openapi: 3.0.0 paths: /v2/playground/images/generations: post: x-hideTryItPanel: true operationId: PlaygroundController_generateImageV2_v2 parameters: [] requestBody: required: true content: application/json: schema: $refId: Image.v1.GenerateImageDTO $ref: '#/components/schemas/Image.v1.GenerateImageDTO' responses: '200': description: Successfully generated image content: application/json: schema: $ref: '#/components/schemas/Image.v1.GenerateImageResponseDTO' tags: &ref_0 - Playground /v2/playground/videos/generations: post: x-hideTryItPanel: true operationId: PlaygroundController_generateVideoV2_v2 parameters: [] requestBody: required: true content: application/json: schema: $refId: Video.v2.SubmitVideoPayload $ref: '#/components/schemas/Video.v2.SubmitVideoPayload' responses: '200': description: Successfully generated video content: application/json: schema: $ref: '#/components/schemas/Video.v2.PollVideoResponseDTO' tags: *ref_0 /v1/playground/audio/generations: post: x-hideTryItPanel: true operationId: PlaygroundController_generateAudio_v1 parameters: [] requestBody: required: true content: application/json: schema: $refId: Audio.v2.SubmitGenerationPayloadDTO $ref: '#/components/schemas/Audio.v2.SubmitGenerationPayloadDTO' responses: '201': description: '' tags: *ref_0 /v1/playground/stt: post: x-hideTryItPanel: true operationId: PlaygroundController_generateSpeechToText_v1 parameters: [] requestBody: required: true content: application/json: schema: $refId: Voice.v1.SpeechToTextPayloadDTO $ref: '#/components/schemas/Voice.v1.SpeechToTextPayloadDTO' responses: '201': description: '' tags: *ref_0 /v1/playground/tts: post: x-hideTryItPanel: true operationId: PlaygroundController_generateTextToSpeech_v1 parameters: [] requestBody: required: true content: application/json: schema: $refId: Voice.v1.TextToSpeechPayload $ref: '#/components/schemas/Voice.v1.TextToSpeechPayload' responses: '201': description: '' tags: *ref_0 /v1/playground/embeddings: post: x-hideTryItPanel: true operationId: PlaygroundController_generateEmbeddings_v1 parameters: [] requestBody: required: true content: application/json: schema: $refId: Embedding.v1.CreateEmbeddingsDTO $ref: '#/components/schemas/Embedding.v1.CreateEmbeddingsDTO' responses: '200': description: Successfully generated embeddings content: application/json: schema: $ref: '#/components/schemas/Embedding.v1.CreateEmbeddingsResponseDTO' tags: *ref_0 /v1/playground/ocr: post: x-hideTryItPanel: true operationId: PlaygroundController_generateOcr_v1 parameters: [] requestBody: required: true content: application/json: schema: $refId: Vision.v1.OCRPayloadDTO $ref: '#/components/schemas/Vision.v1.OCRPayloadDTO' responses: '200': description: Successfully generated ocr content: application/json: schema: $ref: '#/components/schemas/undefined' tags: *ref_0 /v1/models: get: x-hideTryItPanel: true operationId: ModelsController_getModels_v1 parameters: [] responses: '200': description: '' content: application/json: schema: $ref: '#/components/schemas/Model.v1.ModelsResponseDto' tags: &ref_1 - Models /models: get: x-hideTryItPanel: true operationId: ModelsController_getModels parameters: [] responses: '200': description: '' content: application/json: schema: $ref: '#/components/schemas/Model.v1.ModelsResponseDto' tags: *ref_1 /v1/models/with-details: get: x-hideTryItPanel: true operationId: ModelsController_getModelsWithDetails_v1 parameters: [] responses: '200': description: '' content: application/json: schema: $ref: '#/components/schemas/Model.v1.ModelDetailedDto' tags: *ref_1 /models/with-details: get: x-hideTryItPanel: true operationId: ModelsController_getModelsWithDetails parameters: [] responses: '200': description: '' content: application/json: schema: $ref: '#/components/schemas/Model.v1.ModelDetailedDto' tags: *ref_1 info: title: AI/ML Gateway description: '' version: '1.0' contact: {} tags: [] servers: - url: https://api.aimlapi.com components: securitySchemes: access-token: scheme: bearer bearerFormat: type: http description: Bearer key schemas: Image.v1.GenerateImageDTO: anyOf: - type: object properties: model: type: string enum: - dall-e-2 prompt: type: string maxLength: 1000 description: >- The text prompt describing the content, style, or composition of the image to be generated. 'n': type: number minimum: 1 maximum: 10 default: 1 description: The number of images to generate. size: type: string enum: - 1024x1024 - 512x512 - 256x256 default: 1024x1024 description: The size of the generated image. response_format: type: string enum: &ref_2 - url - b64_json default: url description: The format in which the generated images are returned. required: - model - prompt - type: object properties: model: type: string enum: - dall-e-3 prompt: type: string maxLength: 4000 description: >- The text prompt describing the content, style, or composition of the image to be generated. 'n': type: number enum: - 1 default: 1 description: The number of images to generate. quality: type: string enum: - standard - hd default: standard description: The quality of the image that will be generated. size: type: string enum: - 1024x1024 - 1024x1792 - 1792x1024 default: 1024x1024 description: The size of the generated image. style: type: string enum: - vivid - natural default: vivid description: The style of the generated images. response_format: type: string enum: *ref_2 default: url description: The format in which the generated images are returned. required: - model - prompt - $ref: '#/components/schemas/Image.v1.GptImage' - type: object properties: model: type: string enum: - flux/schnell image_size: anyOf: - type: object properties: width: type: integer minimum: 64 maximum: 1536 default: 1024 height: type: integer minimum: 64 maximum: 1536 default: 768 description: >- For both height and width, the value must be a multiple of 32. - type: string enum: &ref_3 - square_hd - square - portrait_4_3 - portrait_16_9 - landscape_4_3 - landscape_16_9 description: The size of the generated image. default: landscape_4_3 num_inference_steps: type: integer minimum: 1 description: The number of inference steps to perform. maximum: 12 enable_safety_checker: type: boolean default: true description: If set to True, the safety checker will be enabled. prompt: type: string maxLength: 4000 description: >- The text prompt describing the content, style, or composition of the image to be generated. num_images: type: number minimum: 1 maximum: 4 default: 1 description: The number of images to generate. seed: type: integer minimum: 1 description: >- The same seed and the same prompt given to the same version of the model will output the same image every time. required: - model - prompt - type: object properties: model: type: string enum: - flux-pro image_size: anyOf: - type: object properties: width: type: integer minimum: 256 maximum: 1440 default: 1024 height: type: integer minimum: 256 maximum: 1440 default: 768 description: >- For both height and width, the value must be a multiple of 32. - type: string enum: *ref_3 description: The size of the generated image. default: landscape_4_3 num_inference_steps: type: integer minimum: 1 maximum: 50 description: The number of inference steps to perform. guidance_scale: type: number minimum: 1 maximum: 20 description: >- The CFG (Classifier Free Guidance) scale is a measure of how close you want the model to stick to your prompt when looking for a related image to show you. safety_tolerance: type: string enum: &ref_4 - '1' - '2' - '3' - '4' - '5' - '6' default: '2' description: >- The safety tolerance level for the generated image. 1 being the most strict and 5 being the most permissive. output_format: type: string enum: &ref_5 - jpeg - png default: jpeg description: The format of the generated image. prompt: type: string maxLength: 4000 description: >- The text prompt describing the content, style, or composition of the image to be generated. num_images: type: number minimum: 1 maximum: 4 default: 1 description: The number of images to generate. seed: type: integer minimum: 1 description: >- The same seed and the same prompt given to the same version of the model will output the same image every time. required: - model - prompt - type: object properties: model: type: string enum: - flux-pro/v1.1 image_size: anyOf: - type: object properties: width: type: integer minimum: 256 maximum: 1440 default: 1024 height: type: integer minimum: 256 maximum: 1440 default: 768 description: >- For both height and width, the value must be a multiple of 32. - type: string enum: *ref_3 description: The size of the generated image. default: landscape_4_3 safety_tolerance: type: string enum: *ref_4 default: '2' description: >- The safety tolerance level for the generated image. 1 being the most strict and 5 being the most permissive. output_format: type: string enum: *ref_5 default: jpeg description: The format of the generated image. prompt: type: string maxLength: 4000 description: >- The text prompt describing the content, style, or composition of the image to be generated. num_images: type: number minimum: 1 maximum: 4 default: 1 description: The number of images to generate. seed: type: integer minimum: 1 description: >- The same seed and the same prompt given to the same version of the model will output the same image every time. enable_safety_checker: type: boolean default: true description: If set to True, the safety checker will be enabled. required: - model - prompt - type: object properties: model: type: string enum: - flux-pro/v1.1-ultra safety_tolerance: type: string enum: *ref_4 default: '2' description: >- The safety tolerance level for the generated image. 1 being the most strict and 5 being the most permissive. output_format: type: string enum: *ref_5 default: jpeg description: The format of the generated image. prompt: type: string maxLength: 4000 description: >- The text prompt describing the content, style, or composition of the image to be generated. num_images: type: number minimum: 1 maximum: 4 default: 1 description: The number of images to generate. seed: type: integer minimum: 1 description: >- The same seed and the same prompt given to the same version of the model will output the same image every time. enable_safety_checker: type: boolean default: true description: If set to True, the safety checker will be enabled. aspect_ratio: type: string enum: &ref_6 - '21:9' - '16:9' - '4:3' - '3:2' - '1:1' - '2:3' - '3:4' - '9:16' - '9:21' default: '16:9' description: The aspect ratio of the generated image. raw: type: boolean enum: - false default: false description: Generate less processed, more natural-looking images. required: - model - prompt - type: object properties: model: type: string enum: - flux-pro/v1.1-ultra-raw safety_tolerance: type: string enum: *ref_4 default: '2' description: >- The safety tolerance level for the generated image. 1 being the most strict and 5 being the most permissive. output_format: type: string enum: *ref_5 default: jpeg description: The format of the generated image. prompt: type: string maxLength: 4000 description: >- The text prompt describing the content, style, or composition of the image to be generated. num_images: type: number minimum: 1 maximum: 4 default: 1 description: The number of images to generate. seed: type: integer minimum: 1 description: >- The same seed and the same prompt given to the same version of the model will output the same image every time. enable_safety_checker: type: boolean default: true description: If set to True, the safety checker will be enabled. aspect_ratio: type: string enum: *ref_6 default: '16:9' description: The aspect ratio of the generated image. raw: type: boolean enum: - true default: true description: Generate less processed, more natural-looking images. required: - model - prompt - type: object properties: model: type: string enum: - flux/dev image_size: anyOf: - type: object properties: width: type: integer minimum: 512 maximum: 1536 default: 1024 height: type: integer minimum: 512 maximum: 1536 default: 768 description: >- For both height and width, the value must be a multiple of 32. - type: string enum: *ref_3 description: The size of the generated image. default: landscape_4_3 guidance_scale: type: number minimum: 1 maximum: 20 description: >- The CFG (Classifier Free Guidance) scale is a measure of how close you want the model to stick to your prompt when looking for a related image to show you. num_inference_steps: type: integer minimum: 1 maximum: 50 description: The number of inference steps to perform. enable_safety_checker: type: boolean default: true description: If set to True, the safety checker will be enabled. prompt: type: string maxLength: 4000 description: >- The text prompt describing the content, style, or composition of the image to be generated. num_images: type: number minimum: 1 maximum: 4 default: 1 description: The number of images to generate. seed: type: integer minimum: 1 description: >- The same seed and the same prompt given to the same version of the model will output the same image every time. required: - model - prompt - type: object properties: model: type: string enum: - flux/dev/image-to-image guidance_scale: type: number minimum: 1 maximum: 20 description: >- The CFG (Classifier Free Guidance) scale is a measure of how close you want the model to stick to your prompt when looking for a related image to show you. num_inference_steps: type: integer minimum: 1 maximum: 50 description: The number of inference steps to perform. enable_safety_checker: type: boolean default: true description: If set to True, the safety checker will be enabled. prompt: type: string maxLength: 4000 description: >- The text prompt describing the content, style, or composition of the image to be generated. num_images: type: number minimum: 1 maximum: 4 default: 1 description: The number of images to generate. seed: type: integer minimum: 1 description: >- The same seed and the same prompt given to the same version of the model will output the same image every time. image_url: type: string format: uri description: The URL of the reference image. strength: type: number default: 0.95 description: Determines how much the prompt influences the generated image. required: - model - prompt - image_url - type: object properties: model: type: string enum: - flux/srpo image_size: anyOf: - type: object properties: width: type: integer minimum: 512 maximum: 1536 default: 1024 height: type: integer minimum: 512 maximum: 1536 default: 768 description: >- For both height and width, the value must be a multiple of 32. - type: string enum: *ref_3 description: The size of the generated image. default: landscape_4_3 num_inference_steps: type: integer minimum: 1 maximum: 50 default: 28 description: The number of inference steps to perform. guidance_scale: type: number minimum: 1 maximum: 20 default: 4.5 description: >- The CFG (Classifier Free Guidance) scale is a measure of how close you want the model to stick to your prompt when looking for a related image to show you. enable_safety_checker: type: boolean default: true description: If set to True, the safety checker will be enabled. output_format: type: string enum: *ref_5 default: jpeg description: The format of the generated image. acceleration: type: string enum: &ref_7 - none - regular - high default: regular description: >- The speed of the generation. The higher the speed, the faster the generation. prompt: type: string maxLength: 4000 description: >- The text prompt describing the content, style, or composition of the image to be generated. num_images: type: number minimum: 1 maximum: 4 default: 1 description: The number of images to generate. seed: type: integer minimum: 1 description: >- The same seed and the same prompt given to the same version of the model will output the same image every time. required: - model - prompt - type: object properties: model: type: string enum: - flux/srpo/image-to-image num_inference_steps: type: integer minimum: 1 maximum: 50 default: 40 description: The number of inference steps to perform. guidance_scale: type: number minimum: 1 maximum: 20 default: 4.5 description: >- The CFG (Classifier Free Guidance) scale is a measure of how close you want the model to stick to your prompt when looking for a related image to show you. enable_safety_checker: type: boolean default: true description: If set to True, the safety checker will be enabled. output_format: type: string enum: *ref_5 default: jpeg description: The format of the generated image. acceleration: type: string enum: *ref_7 default: regular description: >- The speed of the generation. The higher the speed, the faster the generation. prompt: type: string maxLength: 4000 description: >- The text prompt describing the content, style, or composition of the image to be generated. num_images: type: number minimum: 1 maximum: 4 default: 1 description: The number of images to generate. seed: type: integer minimum: 1 description: >- The same seed and the same prompt given to the same version of the model will output the same image every time. image_url: type: string format: uri description: The URL of the reference image. strength: type: number minimum: 0 maximum: 1 default: 0.95 description: Determines how much the prompt influences the generated image. required: - model - prompt - image_url - type: object properties: model: type: string enum: - flux/kontext-pro/text-to-image - flux/kontext-max/text-to-image guidance_scale: type: number minimum: 1 maximum: 20 description: >- The CFG (Classifier Free Guidance) scale is a measure of how close you want the model to stick to your prompt when looking for a related image to show you. safety_tolerance: type: string enum: &ref_8 - '1' - '2' - '3' - '4' - '5' - '6' default: '2' description: >- The safety tolerance level for the generated image. 1 being the most strict and 5 being the most permissive. output_format: type: string enum: *ref_5 default: jpeg description: The format of the generated image. aspect_ratio: type: string enum: *ref_6 default: '16:9' description: The aspect ratio of the generated image. prompt: type: string maxLength: 4000 description: >- The text prompt describing the content, style, or composition of the image to be generated. num_images: type: number minimum: 1 maximum: 4 default: 1 description: The number of images to generate. seed: type: integer minimum: 1 description: >- The same seed and the same prompt given to the same version of the model will output the same image every time. required: - model - prompt - type: object properties: model: type: string enum: - flux/kontext-pro/image-to-image - flux/kontext-max/image-to-image guidance_scale: type: number minimum: 1 maximum: 20 description: >- The CFG (Classifier Free Guidance) scale is a measure of how close you want the model to stick to your prompt when looking for a related image to show you. safety_tolerance: type: string enum: *ref_8 default: '2' description: >- The safety tolerance level for the generated image. 1 being the most strict and 5 being the most permissive. output_format: type: string enum: *ref_5 default: jpeg description: The format of the generated image. aspect_ratio: type: string enum: *ref_6 default: '16:9' description: The aspect ratio of the generated image. prompt: type: string maxLength: 4000 description: >- The text prompt describing the content, style, or composition of the image to be generated. num_images: type: number minimum: 1 maximum: 4 default: 1 description: >- Number of image variations to generate. Each image is a different attempt to combine the reference images (from the image_url parameter) according to the prompt. seed: type: integer minimum: 1 description: >- The same seed and the same prompt given to the same version of the model will output the same image every time. image_url: anyOf: - type: string format: uri - type: array items: type: string format: uri maxItems: 4 description: >- One or more image URLs used as visual references. The model merges them into a single image following the prompt instructions. required: - model - prompt - image_url - $ref: '#/components/schemas/Image.v1.flux2Payload' - $ref: '#/components/schemas/Image.v1.flux2EditPayload' - $ref: '#/components/schemas/Image.v1.flux2LoraPayload' - $ref: '#/components/schemas/Image.v1.flux2LoraEditPayload' - $ref: '#/components/schemas/Image.v1.flux2ProPayload' - $ref: '#/components/schemas/Image.v1.flux2ProEditPayload' - $ref: '#/components/schemas/Image.v1.flux2MaxPayload' - $ref: '#/components/schemas/Image.v1.flux2MaxEditPayload' - type: object properties: model: type: string enum: - stable-diffusion-v3-medium image_size: anyOf: - type: object properties: width: type: integer minimum: 64 maximum: 1536 default: 1024 height: type: integer minimum: 64 maximum: 1536 default: 768 description: >- For both height and width, the value must be a multiple of 32. - type: string enum: *ref_3 description: The size of the generated image. default: square_hd negative_prompt: type: string description: The description of elements to avoid in the generated image. prompt_expansion: type: boolean description: If set to True, prompt will be upsampled with more details. guidance_scale: type: number minimum: 1 maximum: 20 description: >- The CFG (Classifier Free Guidance) scale is a measure of how close you want the model to stick to your prompt when looking for a related image to show you. num_inference_steps: type: integer minimum: 1 maximum: 50 description: The number of inference steps to perform. enable_safety_checker: type: boolean default: true description: If set to True, the safety checker will be enabled. prompt: type: string maxLength: 4000 description: >- The text prompt describing the content, style, or composition of the image to be generated. num_images: type: number minimum: 1 maximum: 4 default: 1 description: The number of images to generate. seed: type: integer minimum: 1 description: >- The same seed and the same prompt given to the same version of the model will output the same image every time. required: - model - prompt - type: object properties: model: type: string enum: - stable-diffusion-v35-large image_size: anyOf: - type: object properties: width: type: integer minimum: 64 maximum: 1536 default: 1024 height: type: integer minimum: 64 maximum: 1536 default: 768 description: >- For both height and width, the value must be a multiple of 32. - type: string enum: *ref_3 description: The size of the generated image. default: square_hd negative_prompt: type: string description: The description of elements to avoid in the generated image. guidance_scale: type: number minimum: 1 maximum: 20 description: >- The CFG (Classifier Free Guidance) scale is a measure of how close you want the model to stick to your prompt when looking for a related image to show you. num_inference_steps: type: integer minimum: 1 maximum: 50 description: The number of inference steps to perform. enable_safety_checker: type: boolean default: true description: If set to True, the safety checker will be enabled. prompt: type: string maxLength: 4000 description: >- The text prompt describing the content, style, or composition of the image to be generated. num_images: type: number minimum: 1 maximum: 4 default: 1 description: The number of images to generate. seed: type: integer minimum: 1 description: >- The same seed and the same prompt given to the same version of the model will output the same image every time. output_format: type: string enum: *ref_5 default: jpeg description: The format of the generated image. required: - model - prompt - type: object properties: model: type: string enum: - flux-realism image_size: anyOf: - type: object properties: width: type: integer minimum: 512 maximum: 1536 default: 1024 height: type: integer minimum: 512 maximum: 1536 default: 768 description: >- For both height and width, the value must be a multiple of 32. - type: string enum: *ref_3 description: The size of the generated image. default: landscape_4_3 guidance_scale: type: number minimum: 1 maximum: 20 description: >- The CFG (Classifier Free Guidance) scale is a measure of how close you want the model to stick to your prompt when looking for a related image to show you. num_inference_steps: type: integer minimum: 1 maximum: 50 description: The number of inference steps to perform. enable_safety_checker: type: boolean default: true description: If set to True, the safety checker will be enabled. output_format: type: string enum: *ref_5 default: jpeg description: The format of the generated image. num_images: type: number enum: - 1 default: 1 description: >- The number of images to generate. This is always set to 1 for streaming output. Default value: 1. prompt: type: string maxLength: 4000 description: >- The text prompt describing the content, style, or composition of the image to be generated. seed: type: integer minimum: 1 description: >- The same seed and the same prompt given to the same version of the model will output the same image every time. required: - model - prompt - type: object properties: model: type: string enum: - triposr image_url: type: string format: uri description: The URL of the reference image. output_format: type: string enum: - glb - obj default: glb description: The format of the generated image. do_remove_background: type: boolean description: Enables removing the background from the input image. foreground_ratio: type: number minimum: 0.5 maximum: 1 default: 0.9 description: Ratio of the foreground image to the original image. mc_resolution: type: integer minimum: 32 maximum: 1024 default: 256 description: Resolution of the marching cubes. Above 512 is not recommended. required: - model - image_url - type: object properties: model: type: string enum: - recraft-v3 prompt: type: string maxLength: 4000 description: >- The text prompt describing the content, style, or composition of the image to be generated. image_size: anyOf: - type: object properties: width: type: integer minimum: 64 maximum: 1536 default: 1024 height: type: integer minimum: 64 maximum: 1536 default: 768 description: >- For both height and width, the value must be a multiple of 32. - type: string enum: *ref_3 description: The size of the generated image. default: square_hd style: type: string enum: - any - realistic_image - digital_illustration - vector_illustration - realistic_image/b_and_w - realistic_image/hard_flash - realistic_image/hdr - realistic_image/natural_light - realistic_image/studio_portrait - realistic_image/enterprise - realistic_image/motion_blur - digital_illustration/pixel_art - digital_illustration/hand_drawn - digital_illustration/grain - digital_illustration/infantile_sketch - digital_illustration/2d_art_poster - digital_illustration/handmade_3d - digital_illustration/hand_drawn_outline - digital_illustration/engraving_color - digital_illustration/2d_art_poster_2 - vector_illustration/engraving - vector_illustration/line_art - vector_illustration/line_circuit - vector_illustration/linocut default: realistic_image description: The style of the generated images. colors: type: array items: type: object properties: r: type: integer minimum: 0 maximum: 255 g: type: integer minimum: 0 maximum: 255 b: type: integer minimum: 0 maximum: 255 required: - r - g - b default: [] description: An array of preferred colors. num_images: type: number enum: - 1 default: 1 description: The number of images to generate. required: - model - prompt - type: object properties: model: type: string enum: - alibaba/qwen-image prompt: type: string maxLength: 4000 description: >- The text prompt describing the content, style, or composition of the image to be generated. output_format: type: string enum: *ref_5 default: jpeg description: The format of the generated image. num_images: type: number minimum: 1 maximum: 4 default: 1 description: The number of images to generate. seed: type: integer minimum: 1 description: >- The same seed and the same prompt given to the same version of the model will output the same image every time. enable_safety_checker: type: boolean default: true description: If set to True, the safety checker will be enabled. guidance_scale: type: number minimum: 1 maximum: 20 description: >- The CFG (Classifier Free Guidance) scale is a measure of how close you want the model to stick to your prompt when looking for a related image to show you. negative_prompt: type: string description: The description of elements to avoid in the generated image. required: - model - prompt - type: object properties: model: type: string enum: - google/gemini-2.5-flash-image prompt: type: string description: >- The text prompt describing the content, style, or composition of the image to be generated. num_images: type: number minimum: 1 maximum: 4 default: 1 description: The number of images to generate. required: - model - prompt - type: object properties: model: type: string enum: - google/gemini-2.5-flash-image-edit prompt: type: string description: >- The text prompt describing the content, style, or composition of the image to be generated. image_urls: type: array items: type: string format: uri description: List of URLs or local Base64 encoded images to edit. aspect_ratio: type: string enum: - '21:9' - '1:1' - '4:3' - '3:2' - '2:3' - '5:4' - '4:5' - '3:4' - '16:9' - '9:16' default: '1:1' description: The aspect ratio of the generated image. num_images: type: number minimum: 1 maximum: 4 default: 1 description: The number of images to generate. required: - model - prompt - image_urls - type: object properties: model: type: string enum: - google/gemini-3-pro-image-preview - google/nano-banana-pro prompt: type: string description: >- The text prompt describing the content, style, or composition of the image to be generated. num_images: type: number minimum: 1 maximum: 4 default: 1 description: The number of images to generate. aspect_ratio: type: string enum: - '21:9' - '1:1' - '4:3' - '3:2' - '2:3' - '5:4' - '4:5' - '3:4' - '16:9' - '9:16' default: '1:1' description: The aspect ratio of the generated image. resolution: type: string enum: - 1K - 2K - 4K default: 1K description: The size of the generated image. required: - model - prompt - type: object properties: model: type: string enum: - google/gemini-3-pro-image-preview-edit - google/nano-banana-pro-edit prompt: type: string description: >- The text prompt describing the content, style, or composition of the image to be generated. image_urls: type: array items: type: string format: uri minItems: 1 description: >- List of URLs or local Base64 encoded images to edit. Supports up to 14 images. aspect_ratio: type: string enum: - auto - '21:9' - '1:1' - '4:3' - '3:2' - '2:3' - '5:4' - '4:5' - '3:4' - '16:9' - '9:16' default: auto description: The aspect ratio of the generated image. num_images: type: number minimum: 1 maximum: 4 default: 1 description: The number of images to generate. resolution: type: string enum: - 1K - 2K - 4K default: 1K description: The size of the generated image. required: - model - prompt - image_urls - type: object properties: model: type: string enum: - bytedance/uso image_urls: type: array items: type: string format: uri minItems: 1 maxItems: 3 description: >- An array of up to 3 image URLs. The first image is always treated as the primary input for image-to-image generation, while the remaining images (if provided) serve as visual style references for the output. image_size: anyOf: - type: string enum: - square_hd - square - portrait_4_3 - portrait_16_9 - landscape_4_3 - landscape_16_9 - type: object properties: width: type: number height: type: number required: - width - height default: square_hd description: The size of the generated image. negative_prompt: type: string default: '' description: The description of elements to avoid in the generated image. num_inference_steps: type: integer minimum: 1 maximum: 50 default: 28 description: The number of inference steps to perform. guidance_scale: type: number minimum: 1 maximum: 20 default: 4 description: >- The CFG (Classifier Free Guidance) scale is a measure of how close you want the model to stick to your prompt when looking for a related image to show you. keep_size: type: boolean num_images: type: number minimum: 1 maximum: 4 default: 1 description: The number of images to generate. seed: type: integer minimum: 1 description: >- The same seed and the same prompt given to the same version of the model will output the same image every time. sync_mode: type: boolean default: false description: >- If set to true, the function will wait for the image to be generated and uploaded before returning the response. This will increase the latency of the function but it allows you to get the image directly in the response without going through the CDN. enable_safety_checker: type: boolean default: true description: If set to True, the safety checker will be enabled. output_format: type: string enum: - jpeg - png default: png description: The format of the generated image. prompt: type: string maxLength: 4000 description: >- The text prompt describing the content, style, or composition of the image to be generated. required: - model - image_urls - prompt - type: object properties: model: type: string enum: - bytedance/seedream-v4-edit image_urls: type: array items: type: string format: uri minItems: 1 maxItems: 10 description: List of URLs or local Base64 encoded images to edit. image_size: anyOf: - type: string enum: - square_hd - square - portrait_4_3 - portrait_16_9 - landscape_4_3 - landscape_16_9 - type: object properties: width: type: number minimum: 1024 maximum: 4096 height: type: number minimum: 1024 maximum: 4096 required: - width - height default: square_hd description: The size of the generated image. seed: type: integer minimum: 1 description: >- The same seed and the same prompt given to the same version of the model will output the same image every time. sync_mode: type: boolean default: false description: >- If set to true, the function will wait for the image to be generated and uploaded before returning the response. This will increase the latency of the function but it allows you to get the image directly in the response without going through the CDN. enable_safety_checker: type: boolean default: true description: If set to True, the safety checker will be enabled. prompt: type: string maxLength: 4000 description: >- The text prompt describing the content, style, or composition of the image to be generated. num_images: type: number minimum: 1 maximum: 4 default: 1 description: The number of images to generate. required: - model - image_urls - prompt - type: object properties: model: type: string enum: - bytedance/seedream-v4-text-to-image image_size: anyOf: - type: string enum: - square_hd - square - portrait_4_3 - portrait_16_9 - landscape_4_3 - landscape_16_9 - type: object properties: width: type: number minimum: 1024 maximum: 4096 height: type: number minimum: 1024 maximum: 4096 required: - width - height default: square_hd description: The size of the generated image. seed: type: integer minimum: 1 description: >- The same seed and the same prompt given to the same version of the model will output the same image every time. sync_mode: type: boolean default: false description: >- If set to true, the function will wait for the image to be generated and uploaded before returning the response. This will increase the latency of the function but it allows you to get the image directly in the response without going through the CDN. enable_safety_checker: type: boolean default: true description: If set to True, the safety checker will be enabled. prompt: type: string maxLength: 4000 description: >- The text prompt describing the content, style, or composition of the image to be generated. num_images: type: number minimum: 1 maximum: 4 default: 1 description: The number of images to generate. required: - model - prompt - type: object properties: model: type: string enum: - hunyuan/hunyuan-image-v3-text-to-image negative_prompt: type: string default: '' description: The description of elements to avoid in the generated image. image_size: anyOf: - type: string enum: - square_hd - square - portrait_4_3 - portrait_16_9 - landscape_4_3 - landscape_16_9 - type: object properties: width: type: number height: type: number required: - width - height default: square_hd description: The size of the generated image. num_inference_steps: type: integer minimum: 1 maximum: 50 default: 28 description: The number of inference steps to perform. guidance_scale: type: number minimum: 1 maximum: 20 default: 7.5 description: >- The CFG (Classifier Free Guidance) scale is a measure of how close you want the model to stick to your prompt when looking for a related image to show you. enable_safety_checker: type: boolean default: true description: If set to True, the safety checker will be enabled. sync_mode: type: boolean default: false description: >- If set to true, the function will wait for the image to be generated and uploaded before returning the response. This will increase the latency of the function but it allows you to get the image directly in the response without going through the CDN. output_format: type: string enum: - jpeg - png default: png description: The format of the generated image. enable_prompt_expansion: type: boolean description: If set to True, prompt will be upsampled with more details. prompt: type: string maxLength: 4000 description: >- The text prompt describing the content, style, or composition of the image to be generated. num_images: type: number minimum: 1 maximum: 4 default: 1 description: The number of images to generate. seed: type: integer minimum: 1 description: >- The same seed and the same prompt given to the same version of the model will output the same image every time. required: - model - prompt - $ref: '#/components/schemas/Image.v1.hunyuanPartPayload' - $ref: '#/components/schemas/Image.v1.zImageTurboPayload' - $ref: '#/components/schemas/Image.v1.zImageTurboLoraPayload' - type: object properties: model: type: string enum: - klingai/image-o1 prompt: type: string maxLength: 4000 description: >- The text prompt describing the content, style, or composition of the image to be generated. image_urls: type: array items: type: string format: uri minItems: 1 maxItems: 10 description: List of URLs or local Base64 encoded images to edit. aspect_ratio: type: string enum: - '21:9' - '16:9' - '4:3' - '3:2' - '1:1' - '2:3' - '3:4' - '9:16' default: '16:9' description: The aspect ratio of the generated image. resolution: type: string enum: - 1K - 2K default: 1K description: The resolution of the output image. output_format: type: string enum: - jpeg - png - webp default: png description: The format of the generated image. num_images: type: number minimum: 1 maximum: 9 default: 1 description: The number of images to generate. required: - model - prompt - image_urls - type: object properties: model: type: string enum: - imagen-3.0-generate-002 prompt: type: string maxLength: 400 description: >- The text prompt describing the content, style, or composition of the image to be generated. convert_base64_to_url: type: boolean default: true description: >- If True, the URL to the image will be returned; otherwise, the file will be provided in base64 format. num_images: type: integer maximum: 4 default: 1 description: The number of images to generate. seed: type: integer minimum: 0 maximum: 4294967295 description: >- The same seed and the same prompt given to the same version of the model will output the same image every time. enhance_prompt: type: boolean default: true description: >- Optional parameter to use an LLM-based prompt rewriting feature for higher-quality images that better match the original prompt. Disabling it may affect image quality and prompt alignment. aspect_ratio: type: string enum: &ref_9 - '1:1' - '9:16' - '16:9' - '3:4' - '4:3' default: '1:1' description: The aspect ratio of the generated image. person_generation: type: string enum: &ref_10 - dont_allow - allow_adult default: allow_adult description: Allow generation of people. safety_setting: type: string enum: &ref_11 - block_low_and_above - block_medium_and_above - block_only_high default: block_medium_and_above description: Adds a filter level to safety filtering. add_watermark: type: boolean default: false description: Add an invisible watermark to the generated images. required: - model - prompt - type: object properties: model: type: string enum: - imagen-4.0-ultra-generate-preview-06-06 prompt: type: string maxLength: 400 description: >- The text prompt describing the content, style, or composition of the image to be generated. convert_base64_to_url: type: boolean default: true description: >- If True, the URL to the image will be returned; otherwise, the file will be provided in base64 format. num_images: type: integer maximum: 4 default: 1 description: The number of images to generate. seed: type: integer minimum: 0 maximum: 4294967295 description: >- The same seed and the same prompt given to the same version of the model will output the same image every time. enhance_prompt: type: boolean default: true description: >- Optional parameter to use an LLM-based prompt rewriting feature for higher-quality images that better match the original prompt. Disabling it may affect image quality and prompt alignment. aspect_ratio: type: string enum: *ref_9 default: '1:1' description: The aspect ratio of the generated image. person_generation: type: string enum: *ref_10 default: allow_adult description: Allow generation of people. safety_setting: type: string enum: *ref_11 default: block_medium_and_above description: Adds a filter level to safety filtering. add_watermark: type: boolean default: false description: Add an invisible watermark to the generated images. required: - model - prompt - type: object properties: model: type: string enum: - google/imagen-4.0-generate-001 - google/imagen4/preview prompt: type: string maxLength: 400 description: >- The text prompt describing the content, style, or composition of the image to be generated. convert_base64_to_url: type: boolean default: true description: >- If True, the URL to the image will be returned; otherwise, the file will be provided in base64 format. num_images: type: integer maximum: 4 default: 1 description: The number of images to generate. seed: type: integer minimum: 0 maximum: 4294967295 description: >- The same seed and the same prompt given to the same version of the model will output the same image every time. enhance_prompt: type: boolean default: true description: >- Optional parameter to use an LLM-based prompt rewriting feature for higher-quality images that better match the original prompt. Disabling it may affect image quality and prompt alignment. aspect_ratio: type: string enum: *ref_9 default: '1:1' description: The aspect ratio of the generated image. person_generation: type: string enum: *ref_10 default: allow_adult description: Allow generation of people. safety_setting: type: string enum: *ref_11 default: block_medium_and_above description: Adds a filter level to safety filtering. add_watermark: type: boolean default: false description: Add an invisible watermark to the generated images. required: - model - prompt - type: object properties: model: type: string enum: - google/imagen-4.0-fast-generate-001 prompt: type: string maxLength: 400 description: >- The text prompt describing the content, style, or composition of the image to be generated. convert_base64_to_url: type: boolean default: true description: >- If True, the URL to the image will be returned; otherwise, the file will be provided in base64 format. num_images: type: integer maximum: 4 default: 1 description: The number of images to generate. seed: type: integer minimum: 0 maximum: 4294967295 description: >- The same seed and the same prompt given to the same version of the model will output the same image every time. enhance_prompt: type: boolean default: true description: >- Optional parameter to use an LLM-based prompt rewriting feature for higher-quality images that better match the original prompt. Disabling it may affect image quality and prompt alignment. aspect_ratio: type: string enum: *ref_9 default: '1:1' description: The aspect ratio of the generated image. person_generation: type: string enum: *ref_10 default: allow_adult description: Allow generation of people. safety_setting: type: string enum: *ref_11 default: block_medium_and_above description: Adds a filter level to safety filtering. add_watermark: type: boolean default: false description: Add an invisible watermark to the generated images. required: - model - prompt - type: object properties: model: type: string enum: - google/imagen-4.0-ultra-generate-001 prompt: type: string maxLength: 400 description: >- The text prompt describing the content, style, or composition of the image to be generated. convert_base64_to_url: type: boolean default: true description: >- If True, the URL to the image will be returned; otherwise, the file will be provided in base64 format. num_images: type: integer maximum: 4 default: 1 description: The number of images to generate. seed: type: integer minimum: 0 maximum: 4294967295 description: >- The same seed and the same prompt given to the same version of the model will output the same image every time. enhance_prompt: type: boolean default: true description: >- Optional parameter to use an LLM-based prompt rewriting feature for higher-quality images that better match the original prompt. Disabling it may affect image quality and prompt alignment. aspect_ratio: type: string enum: *ref_9 default: '1:1' description: The aspect ratio of the generated image. person_generation: type: string enum: *ref_10 default: allow_adult description: Allow generation of people. safety_setting: type: string enum: *ref_11 default: block_medium_and_above description: Adds a filter level to safety filtering. add_watermark: type: boolean default: false description: Add an invisible watermark to the generated images. required: - model - prompt - type: object properties: model: type: string enum: - google/gemini-2.5-flash-image prompt: type: string maxLength: 400 description: >- The text prompt describing the content, style, or composition of the image to be generated. convert_base64_to_url: type: boolean default: true description: >- If True, the URL to the image will be returned; otherwise, the file will be provided in base64 format. num_images: type: integer maximum: 4 default: 1 description: The number of images to generate. seed: type: integer minimum: 0 maximum: 4294967295 description: >- The same seed and the same prompt given to the same version of the model will output the same image every time. enhance_prompt: type: boolean default: true description: >- Optional parameter to use an LLM-based prompt rewriting feature for higher-quality images that better match the original prompt. Disabling it may affect image quality and prompt alignment. aspect_ratio: type: string enum: *ref_9 default: '1:1' description: The aspect ratio of the generated image. person_generation: type: string enum: *ref_10 default: allow_adult description: Allow generation of people. safety_setting: type: string enum: *ref_11 default: block_medium_and_above description: Adds a filter level to safety filtering. add_watermark: type: boolean default: false description: Add an invisible watermark to the generated images. required: - model - prompt - type: object properties: model: type: string enum: - google/gemini-2.5-flash-image-edit image_urls: type: array items: type: string format: uri minItems: 1 description: URLs of the source images to edit prompt: type: string maxLength: 400 description: >- The text prompt describing the content, style, or composition of the image to be generated. convert_base64_to_url: type: boolean default: true description: >- If True, the URL to the image will be returned; otherwise, the file will be provided in base64 format. num_images: type: integer maximum: 4 default: 1 description: The number of images to generate. seed: type: integer minimum: 0 maximum: 4294967295 description: >- The same seed and the same prompt given to the same version of the model will output the same image every time. enhance_prompt: type: boolean default: true description: >- Optional parameter to use an LLM-based prompt rewriting feature for higher-quality images that better match the original prompt. Disabling it may affect image quality and prompt alignment. aspect_ratio: type: string enum: &ref_12 - auto - '1:1' - '9:16' - '16:9' - '3:4' - '4:3' default: auto description: The aspect ratio of the generated image. person_generation: type: string enum: *ref_10 default: allow_adult description: Allow generation of people. safety_setting: type: string enum: *ref_11 default: block_medium_and_above description: Adds a filter level to safety filtering. add_watermark: type: boolean default: false description: Add an invisible watermark to the generated images. required: - model - image_urls - prompt - type: object properties: model: type: string enum: - google/gemini-3-pro-image-preview - google/nano-banana-pro prompt: type: string maxLength: 400 description: >- The text prompt describing the content, style, or composition of the image to be generated. convert_base64_to_url: type: boolean default: true description: >- If True, the URL to the image will be returned; otherwise, the file will be provided in base64 format. num_images: type: integer maximum: 4 default: 1 description: The number of images to generate. seed: type: integer minimum: 0 maximum: 4294967295 description: >- The same seed and the same prompt given to the same version of the model will output the same image every time. enhance_prompt: type: boolean default: true description: >- Optional parameter to use an LLM-based prompt rewriting feature for higher-quality images that better match the original prompt. Disabling it may affect image quality and prompt alignment. aspect_ratio: type: string enum: *ref_9 default: '1:1' description: The aspect ratio of the generated image. person_generation: type: string enum: *ref_10 default: allow_adult description: Allow generation of people. safety_setting: type: string enum: *ref_11 default: block_medium_and_above description: Adds a filter level to safety filtering. add_watermark: type: boolean default: false description: Add an invisible watermark to the generated images. required: - model - prompt - type: object properties: model: type: string enum: - google/gemini-3-pro-image-preview-edit - google/nano-banana-pro-edit image_urls: type: array items: type: string format: uri minItems: 1 description: URLs of the source images to edit prompt: type: string maxLength: 400 description: >- The text prompt describing the content, style, or composition of the image to be generated. convert_base64_to_url: type: boolean default: true description: >- If True, the URL to the image will be returned; otherwise, the file will be provided in base64 format. num_images: type: integer maximum: 4 default: 1 description: The number of images to generate. seed: type: integer minimum: 0 maximum: 4294967295 description: >- The same seed and the same prompt given to the same version of the model will output the same image every time. enhance_prompt: type: boolean default: true description: >- Optional parameter to use an LLM-based prompt rewriting feature for higher-quality images that better match the original prompt. Disabling it may affect image quality and prompt alignment. aspect_ratio: type: string enum: *ref_12 default: auto description: The aspect ratio of the generated image. person_generation: type: string enum: *ref_10 default: allow_adult description: Allow generation of people. safety_setting: type: string enum: *ref_11 default: block_medium_and_above description: Adds a filter level to safety filtering. add_watermark: type: boolean default: false description: Add an invisible watermark to the generated images. required: - model - image_urls - prompt - oneOf: - type: object properties: provider: type: string enum: - bytedance default: bytedance deprecated: true model: type: string enum: - bytedance/seedream-4-5 prompt: type: string description: >- The text prompt describing the content, style, or composition of the image to be generated. image_urls: type: array items: type: string format: uri minItems: 1 maxItems: 14 description: List of URLs or local Base64 encoded images to edit. image_size: anyOf: - type: object properties: width: type: integer minimum: 1440 maximum: 4096 default: 2048 height: type: integer minimum: 1440 maximum: 4096 default: 2048 - type: string enum: - 2K - 4K response_format: type: string enum: - url - b64_json default: url description: The format in which the generated images are returned. seed: type: integer description: >- The same seed and the same prompt given to the same version of the model will output the same image every time. watermark: type: boolean default: false description: Add an invisible watermark to the generated images. required: - model - prompt - type: object properties: provider: type: string enum: - bytedance default: bytedance deprecated: true model: type: string enum: - bytedance/seedream-5-0-lite-preview prompt: type: string description: >- The text prompt describing the content, style, or composition of the image to be generated. image_urls: type: array items: type: string format: uri minItems: 1 maxItems: 14 description: List of URLs or local Base64 encoded images to edit. image_size: anyOf: - type: object properties: width: type: integer minimum: 1440 maximum: 4096 default: 2048 height: type: integer minimum: 1440 maximum: 4096 default: 2048 - type: string enum: - 2K - 4K description: The size of the generated image. response_format: type: string enum: - url - b64_json default: url description: The format in which the generated images are returned. seed: type: integer description: >- The same seed and the same prompt given to the same version of the model will output the same image every time. watermark: type: boolean default: false description: Add an invisible watermark to the generated images. required: - model - prompt - oneOf: - type: object properties: model: type: string enum: - alibaba/qwen-image-edit provider: type: string enum: - alibaba default: alibaba deprecated: true prompt: type: string maxLength: 800 description: >- A positive prompt that describes the desired elements and visual features in the edited image. Maximum 800 characters. image: type: string description: >- The image to be edited. Enter the Base64 encoding of the picture or an accessible URL. Image URL: Make sure that the image URL is accessible. Base64-encoded content: The format must be in lowercase. negative_prompt: type: string maxLength: 500 description: The description of elements to avoid in the generated image. watermark: type: boolean default: false description: Add an invisible watermark to the generated images. required: - model - prompt - image - type: object properties: provider: type: string enum: - alibaba default: alibaba deprecated: true model: type: string enum: - alibaba/wan-2-6-image prompt: type: string maxLength: 2000 description: >- A positive prompt that describes the desired elements and visual features in the edited image. image_urls: type: array items: type: string format: uri minItems: 1 maxItems: 3 description: List of URLs or local Base64 encoded images to edit. image_size: anyOf: - type: object properties: width: type: integer minimum: 512 maximum: 1440 height: type: integer minimum: 512 maximum: 1440 required: - width - height description: >- For both height and width, the value must be a multiple of 32. - type: string enum: &ref_13 - square_hd - square - portrait_4_3 - portrait_16_9 - landscape_4_3 - landscape_16_9 description: The size of the generated image. default: landscape_4_3 description: The size of the generated image. enhance_prompt: type: boolean default: true description: >- Optional parameter to use an LLM-based prompt rewriting feature for higher-quality images that better match the original prompt. Disabling it may affect image quality and prompt alignment. negative_prompt: type: string maxLength: 500 description: The description of elements to avoid in the generated image. seed: type: integer minimum: 0 maximum: 2147483647 description: >- The same seed and the same prompt given to the same version of the model will output the same image every time. watermark: type: boolean default: false description: Add an invisible watermark to the generated images. required: - model - prompt - type: object properties: prompt: type: string maxLength: 800 description: >- The text prompt describing the content, style, or composition of the image to be generated. negative_prompt: type: string maxLength: 500 description: The description of elements to avoid in the generated image. num_images: type: integer minimum: 1 maximum: 4 default: 1 description: The number of images to generate. image_size: anyOf: - type: object properties: width: type: integer minimum: 512 maximum: 1664 height: type: integer minimum: 512 maximum: 1664 required: - width - height description: >- For both height and width, the value must be a multiple of 32. - type: string enum: *ref_13 description: The size of the generated image. default: width: 1664 height: 928 description: The size of the generated image. watermark: type: boolean default: false description: Add an invisible watermark to the generated images. seed: type: integer minimum: 0 maximum: 2147483647 description: >- The same seed and the same prompt given to the same version of the model will output the same image every time. model: type: string enum: - alibaba/qwen-image output_format: type: string enum: - jpeg - png default: jpeg description: The format of the generated image. prompt_extend: type: boolean default: true description: If set to True, prompt will be upsampled with more details. enable_safety_checker: type: boolean default: true description: If set to True, the safety checker will be enabled. guidance_scale: type: number minimum: 1 maximum: 20 description: >- The CFG (Classifier Free Guidance) scale is a measure of how close you want the model to stick to your prompt when looking for a related image to show you. required: - prompt - model - type: object properties: prompt: type: string maxLength: 800 description: >- The text prompt describing the content, style, or composition of the image to be generated. negative_prompt: type: string maxLength: 500 description: The description of elements to avoid in the generated image. num_images: type: integer minimum: 1 maximum: 4 default: 1 description: The number of images to generate. image_size: anyOf: - type: object properties: width: type: integer minimum: 512 maximum: 2048 height: type: integer minimum: 512 maximum: 2048 required: - width - height description: >- For both height and width, the value must be a multiple of 32. - type: string enum: *ref_13 description: The size of the generated image. default: width: 1024 height: 1536 description: The size of the generated image. watermark: type: boolean default: false description: Add an invisible watermark to the generated images. seed: type: integer minimum: 0 maximum: 2147483647 description: >- The same seed and the same prompt given to the same version of the model will output the same image every time. model: type: string enum: - alibaba/z-image-turbo output_format: type: string enum: - jpeg - png - webp default: png description: The format of the generated image. num_inference_steps: type: integer minimum: 1 maximum: 8 description: The number of inference steps to perform. enable_safety_checker: type: boolean default: true description: If set to True, the safety checker will be enabled. acceleration: type: string enum: - none - regular - high default: regular description: >- The speed of the generation. The higher the speed, the faster the generation. prompt_extend: type: boolean default: false description: If set to True, prompt will be upsampled with more details. required: - prompt - model - type: object properties: model: type: string enum: - alibaba/wan2.5-t2i-preview prompt: type: string maxLength: 2000 description: >- The text prompt describing the content, style, or composition of the image to be generated. negative_prompt: type: string maxLength: 500 description: The description of elements to avoid in the generated image. num_images: type: integer minimum: 1 maximum: 4 default: 1 description: The number of images to generate. image_size: anyOf: - type: object properties: width: type: integer minimum: 512 maximum: 1440 height: type: integer minimum: 512 maximum: 1440 required: - width - height description: >- For both height and width, the value must be a multiple of 32. - type: string enum: *ref_13 description: The size of the generated image. default: landscape_4_3 description: The size of the generated image. enhance_prompt: type: boolean default: true description: >- Optional parameter to use an LLM-based prompt rewriting feature for higher-quality images that better match the original prompt. Disabling it may affect image quality and prompt alignment. watermark: type: boolean default: false description: Add an invisible watermark to the generated images. seed: type: integer minimum: 0 maximum: 2147483647 description: >- The same seed and the same prompt given to the same version of the model will output the same image every time. required: - model - prompt - type: object properties: model: type: string enum: - alibaba/wan2.2-t2i-plus prompt: type: string maxLength: 2000 description: >- The text prompt describing the content, style, or composition of the image to be generated. negative_prompt: type: string maxLength: 500 description: The description of elements to avoid in the generated image. num_images: type: integer minimum: 1 maximum: 4 default: 1 description: The number of images to generate. image_size: anyOf: - type: object properties: width: type: integer minimum: 512 maximum: 1440 height: type: integer minimum: 512 maximum: 1440 required: - width - height description: >- For both height and width, the value must be a multiple of 32. - type: string enum: *ref_13 description: The size of the generated image. default: landscape_4_3 description: The size of the generated image. enhance_prompt: type: boolean default: true description: >- Optional parameter to use an LLM-based prompt rewriting feature for higher-quality images that better match the original prompt. Disabling it may affect image quality and prompt alignment. watermark: type: boolean default: false description: Add an invisible watermark to the generated images. seed: type: integer minimum: 0 maximum: 2147483647 description: >- The same seed and the same prompt given to the same version of the model will output the same image every time. required: - model - prompt - type: object properties: model: type: string enum: - alibaba/wan2.2-t2i-flash prompt: type: string maxLength: 2000 description: >- The text prompt describing the content, style, or composition of the image to be generated. negative_prompt: type: string maxLength: 500 description: The description of elements to avoid in the generated image. num_images: type: integer minimum: 1 maximum: 4 default: 1 description: The number of images to generate. image_size: anyOf: - type: object properties: width: type: integer minimum: 512 maximum: 1440 height: type: integer minimum: 512 maximum: 1440 required: - width - height description: >- For both height and width, the value must be a multiple of 32. - type: string enum: *ref_13 description: The size of the generated image. default: landscape_4_3 description: The size of the generated image. enhance_prompt: type: boolean default: true description: >- Optional parameter to use an LLM-based prompt rewriting feature for higher-quality images that better match the original prompt. Disabling it may affect image quality and prompt alignment. watermark: type: boolean default: false description: Add an invisible watermark to the generated images. seed: type: integer minimum: 0 maximum: 2147483647 description: >- The same seed and the same prompt given to the same version of the model will output the same image every time. required: - model - prompt - type: object properties: model: type: string enum: - openai/gpt-image-1 prompt: type: string maxLength: 32000 description: >- The text prompt describing the content, style, or composition of the image to be generated. background: type: string enum: - transparent - opaque - auto default: auto description: >- Allows to set transparency for the background of the generated image(s). When auto is used, the model will automatically determine the best background for the image. If transparent, the output format needs to support transparency, so it should be set to either png (default value) or webp. moderation: type: string enum: - low - auto default: auto description: Control the content-moderation level for images. 'n': type: number enum: - 1 default: 1 description: The number of images to generate. deprecated: true output_compression: type: integer minimum: 0 maximum: 100 default: 100 description: The compression level (0-100%) for the generated images. output_format: type: string enum: &ref_17 - png - jpeg - webp default: png description: The format of the generated image. quality: type: string enum: &ref_18 - low - medium - high default: medium description: The quality of the image that will be generated. size: type: string enum: &ref_19 - 1024x1024 - 1024x1536 - 1536x1024 default: 1024x1024 description: The size of the generated image. response_format: type: string enum: - url - b64_json default: url description: The format in which the generated images are returned. required: - model - prompt - type: object properties: model: type: string enum: - bytedance/seedream-3.0 prompt: type: string description: >- The text prompt describing the content, style, or composition of the image to be generated. aspect_ratio: type: string enum: - '1:1' - '16:9' - '9:16' - '3:4' - '4:3' default: '1:1' description: The aspect ratio of the generated image. seed: type: integer description: >- The same seed and the same prompt given to the same version of the model will output the same image every time. guidance_scale: type: number minimum: 1 maximum: 10 default: 2.5 description: >- The CFG (Classifier Free Guidance) scale is a measure of how close you want the model to stick to your prompt when looking for a related image to show you. response_format: type: string enum: - url - b64_json default: url description: The format in which the generated images are returned. size: type: string description: >- Specifies the dimensions (width x height in pixels) of the generated image. Must be between [512x512, 2048x2048]. example: 1024x1024 deprecated: true watermark: type: boolean default: false description: Add an invisible watermark to the generated images. deprecated: true required: - model - prompt - type: object properties: model: type: string enum: - reve/create-image aspect_ratio: type: string enum: - '16:9' - '9:16' - '3:2' - '2:3' - '4:3' - '3:4' - '1:1' default: '3:2' description: The aspect ratio of the generated image. prompt: type: string maxLength: 2560 description: >- The text prompt describing the content, style, or composition of the image to be generated. convert_base64_to_url: type: boolean default: true description: >- If True, the URL to the image will be returned; otherwise, the file will be provided in base64 format. required: - model - prompt - type: object properties: model: type: string enum: - reve/edit-image image_url: type: string format: uri description: The URL of the reference image. prompt: type: string maxLength: 2560 description: >- The text prompt describing the content, style, or composition of the image to be generated. convert_base64_to_url: type: boolean default: true description: >- If True, the URL to the image will be returned; otherwise, the file will be provided in base64 format. required: - model - image_url - prompt - type: object properties: model: type: string enum: - reve/remix-edit-image image_urls: type: array items: type: string format: uri minItems: 1 maxItems: 4 description: List of URLs or local Base64 encoded images to edit. aspect_ratio: type: string enum: - '16:9' - '9:16' - '3:2' - '2:3' - '4:3' - '3:4' - '1:1' default: '3:2' description: The aspect ratio of the generated image. prompt: type: string maxLength: 2560 description: >- The text prompt describing the content, style, or composition of the image to be generated. convert_base64_to_url: type: boolean default: true description: >- If True, the URL to the image will be returned; otherwise, the file will be provided in base64 format. required: - model - image_urls - prompt - type: object properties: model: type: string enum: - topaz-labs/sharpen mode: type: string enum: - Standard - Strong - Lens Blur - Lens Blur V2 - Motion Blur - Natural - Refocus image_url: type: string format: uri description: The URL of the reference image. strength: type: number minimum: 0.01 maximum: 1 description: >- Defines the overall intensity of the sharpening effect. Increases details. Too much sharpening can create an unrealistic result. minor_denoise: type: number minimum: 0.01 maximum: 1 description: >- Removes noisy pixels to increase clarity. Can slightly increase image sharpness. output_format: type: string enum: &ref_14 - jpeg - jpg - png - tiff - tif default: jpeg description: The format of the generated image. subject_detection: type: string enum: &ref_15 - All - Foreground - Background default: All description: >- Specifies which subjects to detect and process. Options: 'All' (detect all subjects), 'Foreground' (detect only foreground subjects), 'Background' (detect background subjects). face_enhancement: type: boolean default: true description: >- Whether to enhance faces in the image. When true, the model applies face-specific improvements. face_enhancement_creativity: type: number minimum: 0 maximum: 1 default: 0 description: >- Level of creativity for face enhancement (0-1). Higher values allow more creative, less conservative changes. face_enhancement_strength: type: number minimum: 0 maximum: 1 default: 0.8 description: >- How sharp enhanced faces are relative to background (0-1). Lower values blend changes subtly; higher values make faces more pronounced. required: - model - mode - image_url - type: object properties: model: type: string enum: - topaz-labs/sharpen-gen mode: type: string enum: - Super Focus - Super Focus V2 image_url: type: string format: uri description: The URL of the reference image. strength: type: number minimum: 0 maximum: 1 description: >- Defines the overall intensity of the sharpening effect. Increases details. Too much sharpening can create an unrealistic result. focus_boost: type: number minimum: 0.25 maximum: 1 description: >- Corrects images that are missing detail by downscaling your image then upscaling the results back to the original size. Use on very blurry images! seed: type: integer description: Optional fixed seed for repeatable results. output_format: type: string enum: *ref_14 default: jpeg description: The format of the generated image. subject_detection: type: string enum: *ref_15 default: All description: >- Specifies which subjects to detect and process. Options: 'All' (detect all subjects), 'Foreground' (detect only foreground subjects), 'Background' (detect background subjects). face_enhancement: type: boolean default: true description: >- Whether to enhance faces in the image. When true, the model applies face-specific improvements. face_enhancement_creativity: type: number minimum: 0 maximum: 1 default: 0 description: >- Level of creativity for face enhancement (0-1). Higher values allow more creative, less conservative changes. face_enhancement_strength: type: number minimum: 0 maximum: 1 default: 0.8 description: >- How sharp enhanced faces are relative to background (0-1). Lower values blend changes subtly; higher values make faces more pronounced. required: - model - mode - image_url - type: object properties: prompt: type: string description: >- The text prompt describing the content, style, or composition of the image to be generated. 'n': type: number minimum: 1 maximum: 10 default: 1 description: The number of images to generate. response_format: type: string enum: &ref_16 - url - b64_json default: url description: The format in which the generated images are returned. model: type: string enum: - x-ai/grok-2-image required: - prompt - model - type: object properties: prompt: type: string description: >- The text prompt describing the content, style, or composition of the image to be generated. 'n': type: number minimum: 1 maximum: 10 default: 1 description: The number of images to generate. response_format: type: string enum: *ref_16 default: url description: The format in which the generated images are returned. model: type: string enum: - x-ai/grok-imagine-image - x-ai/grok-imagine-image-pro aspect_ratio: type: string enum: - '1:1' - '3:4' - '4:3' - '9:16' - '16:9' - '2:3' - '3:2' - '9:19.5' - 19.5:9 - '9:20' - '20:9' - '1:2' - '2:1' - auto default: '16:9' description: The aspect ratio of the generated image. resolution: type: string enum: - 1k - 2k default: 2k description: The resolution of the output image. required: - prompt - model - type: object properties: model: type: string enum: - magic/image-to-3d front_image_url: type: string format: uri left_image_url: type: string format: uri back_image_url: type: string format: uri right_image_url: type: string format: uri required: - model - front_image_url Image.v1.GptImage: type: object properties: model: type: string enum: - openai/gpt-image-1 - openai/gpt-image-1-mini - openai/gpt-image-1-5 prompt: type: string maxLength: 32000 description: >- The text prompt describing the content, style, or composition of the image to be generated. background: type: string enum: - transparent - opaque - auto default: auto description: >- Allows to set transparency for the background of the generated image(s). When auto is used, the model will automatically determine the best background for the image. If transparent, the output format needs to support transparency, so it should be set to either png (default value) or webp. moderation: type: string enum: - low - auto default: auto description: Control the content-moderation level for images. 'n': type: number enum: - 1 default: 1 description: The number of images to generate. deprecated: true output_compression: type: integer minimum: 0 maximum: 100 default: 100 description: The compression level (0-100%) for the generated images. output_format: type: string enum: *ref_17 default: png description: The format of the generated image. quality: type: string enum: *ref_18 default: medium description: The quality of the image that will be generated. size: type: string enum: *ref_19 default: 1024x1024 description: The size of the generated image. response_format: type: string enum: *ref_2 default: url description: The format in which the generated images are returned. required: - model - prompt Image.v1.flux2Payload: type: object properties: model: type: string enum: - blackforestlabs/flux-2 prompt: type: string maxLength: 4000 description: >- The text prompt describing the content, style, or composition of the image to be generated. num_images: type: number minimum: 1 maximum: 4 default: 1 description: The number of images to generate. seed: type: integer minimum: 1 description: >- The same seed and the same prompt given to the same version of the model will output the same image every time. guidance_scale: type: number minimum: 0 maximum: 20 description: >- The CFG (Classifier Free Guidance) scale is a measure of how close you want the model to stick to your prompt when looking for a related image to show you. num_inference_steps: type: integer minimum: 4 maximum: 50 description: The number of inference steps to perform. image_size: anyOf: - type: object properties: width: type: integer minimum: 512 maximum: 2048 default: 1024 height: type: integer minimum: 512 maximum: 2048 default: 768 description: For both height and width, the value must be a multiple of 32. - type: string enum: *ref_3 description: The size of the generated image. default: landscape_4_3 acceleration: type: string enum: - none - regular - high default: regular description: >- The speed of the generation. The higher the speed, the faster the generation. enable_prompt_expansion: type: boolean description: If set to True, prompt will be upsampled with more details. enable_safety_checker: type: boolean default: true description: If set to True, the safety checker will be enabled. output_format: type: string enum: - jpeg - png - webp default: png description: The format of the generated image. required: - model - prompt Image.v1.flux2EditPayload: type: object properties: model: type: string enum: - blackforestlabs/flux-2-edit prompt: type: string maxLength: 4000 description: >- The text prompt describing the content, style, or composition of the image to be generated. image_urls: type: array items: type: string format: uri minItems: 1 maxItems: 3 description: >- An array of up to 3 image URLs. The first image is always treated as the primary input for image-to-image generation, while the remaining images (if provided) serve as visual style references for the output. num_images: type: number minimum: 1 maximum: 4 default: 1 description: The number of images to generate. seed: type: integer minimum: 1 description: >- The same seed and the same prompt given to the same version of the model will output the same image every time. guidance_scale: type: number minimum: 0 maximum: 20 description: >- The CFG (Classifier Free Guidance) scale is a measure of how close you want the model to stick to your prompt when looking for a related image to show you. num_inference_steps: type: integer minimum: 4 maximum: 50 description: The number of inference steps to perform. image_size: anyOf: - type: object properties: width: type: integer minimum: 512 maximum: 2048 default: 1024 height: type: integer minimum: 512 maximum: 2048 default: 768 description: For both height and width, the value must be a multiple of 32. - type: string enum: *ref_3 description: The size of the generated image. default: landscape_4_3 acceleration: type: string enum: - none - regular - high default: regular description: >- The speed of the generation. The higher the speed, the faster the generation. enable_prompt_expansion: type: boolean description: If set to True, prompt will be upsampled with more details. enable_safety_checker: type: boolean default: true description: If set to True, the safety checker will be enabled. output_format: type: string enum: - jpeg - png - webp default: png description: The format of the generated image. required: - model - prompt - image_urls Image.v1.flux2LoraPayload: allOf: - $ref: '#/components/schemas/Image.v1.flux2Payload' - type: object properties: model: type: string enum: - blackforestlabs/flux-2-lora loras: type: array items: type: object properties: path: type: string description: URL, HuggingFace repo ID (owner/repo). scale: type: number minimum: 0 maximum: 4 description: Scale factor for LoRA application. required: - path maxItems: 3 description: >- List of LoRA weights to apply (maximum 3). Each LoRA can be a URL, HuggingFace repo ID, or local path. Image.v1.flux2LoraEditPayload: allOf: - $ref: '#/components/schemas/Image.v1.flux2EditPayload' - type: object properties: model: type: string enum: - blackforestlabs/flux-2-lora-edit loras: type: array items: type: object properties: path: type: string description: URL, HuggingFace repo ID (owner/repo). scale: type: number minimum: 0 maximum: 4 description: Scale factor for LoRA application. required: - path maxItems: 3 description: >- List of LoRA weights to apply (maximum 3). Each LoRA can be a URL, HuggingFace repo ID, or local path. Image.v1.flux2ProPayload: type: object properties: model: type: string enum: - blackforestlabs/flux-2-pro prompt: type: string maxLength: 4000 description: >- The text prompt describing the content, style, or composition of the image to be generated. image_size: anyOf: - type: object properties: width: type: integer minimum: 512 maximum: 2048 default: 1024 height: type: integer minimum: 512 maximum: 2048 default: 768 description: For both height and width, the value must be a multiple of 32. - type: string enum: *ref_3 description: The size of the generated image. default: landscape_4_3 enable_safety_checker: type: boolean default: true description: If set to True, the safety checker will be enabled. seed: type: integer minimum: 1 description: >- The same seed and the same prompt given to the same version of the model will output the same image every time. safety_tolerance: type: string enum: - '1' - '2' - '3' - '4' - '5' - '6' default: '2' description: >- The safety tolerance level for the generated image. 1 being the most strict and 5 being the most permissive. output_format: type: string enum: - jpeg - png - webp default: png description: The format of the generated image. required: - model - prompt Image.v1.flux2ProEditPayload: allOf: - $ref: '#/components/schemas/Image.v1.flux2ProPayload' - type: object properties: model: type: string enum: - blackforestlabs/flux-2-pro-edit image_urls: type: array items: type: string format: uri minItems: 1 maxItems: 3 description: >- An array of up to 3 image URLs. The first image is always treated as the primary input for image-to-image generation, while the remaining images (if provided) serve as visual style references for the output. required: - image_urls Image.v1.flux2MaxPayload: type: object properties: model: type: string enum: - blackforestlabs/flux-2-max prompt: type: string maxLength: 4000 description: >- The text prompt describing the content, style, or composition of the image to be generated. image_size: anyOf: - type: object properties: width: type: integer minimum: 512 maximum: 2048 default: 1024 height: type: integer minimum: 512 maximum: 2048 default: 768 description: For both height and width, the value must be a multiple of 32. - type: string enum: *ref_3 description: The size of the generated image. default: landscape_4_3 enable_safety_checker: type: boolean default: true description: If set to True, the safety checker will be enabled. seed: type: integer minimum: 1 description: >- The same seed and the same prompt given to the same version of the model will output the same image every time. safety_tolerance: type: string enum: - '1' - '2' - '3' - '4' - '5' default: '2' description: >- The safety tolerance level for the generated image. 1 being the most strict and 5 being the most permissive. output_format: type: string enum: - jpeg - png default: jpeg description: The format of the generated image. required: - model - prompt Image.v1.flux2MaxEditPayload: type: object properties: model: type: string enum: - blackforestlabs/flux-2-max-edit prompt: type: string maxLength: 4000 description: >- The text prompt describing the content, style, or composition of the image to be generated. image_urls: type: array items: type: string format: uri minItems: 1 description: List of URLs or local Base64 encoded images to edit. image_size: anyOf: - type: object properties: width: type: integer minimum: 512 maximum: 2048 default: 1024 height: type: integer minimum: 512 maximum: 2048 default: 768 description: For both height and width, the value must be a multiple of 32. - type: string enum: *ref_3 description: The size of the generated image. default: landscape_4_3 enable_safety_checker: type: boolean default: true description: If set to True, the safety checker will be enabled. seed: type: integer minimum: 1 description: >- The same seed and the same prompt given to the same version of the model will output the same image every time. safety_tolerance: type: string enum: - '1' - '2' - '3' - '4' - '5' default: '2' description: >- The safety tolerance level for the generated image. 1 being the most strict and 5 being the most permissive. output_format: type: string enum: - jpeg - png default: jpeg description: The format of the generated image. required: - model - prompt - image_urls Image.v1.hunyuanPartPayload: type: object properties: model: type: string enum: - tencent/hunyuan-part mesh_url: type: string format: uri description: URL of the 3D model file (.glb or .obj) to process for segmentation. point_prompt_x: type: number minimum: -1 maximum: 1 description: X coordinate of the point prompt for segmentation. point_prompt_y: type: number minimum: -1 maximum: 1 description: Y coordinate of the point prompt for segmentation. point_prompt_z: type: number minimum: -1 maximum: 1 description: Z coordinate of the point prompt for segmentation. point_num: type: integer default: 100000 description: Number of points to sample from the mesh. use_normal: type: boolean default: true description: Whether to use normal information for segmentation. noise_std: type: number description: Standard deviation of noise to add to sampled points. seed: type: integer minimum: 1 description: >- The same seed and the same prompt given to the same version of the model will output the same image every time. required: - model - mesh_url Image.v1.zImageTurboPayload: type: object properties: model: type: string enum: - alibaba/z-image-turbo prompt: type: string maxLength: 4000 description: >- The text prompt describing the content, style, or composition of the image to be generated. image_size: anyOf: - type: object properties: width: type: integer minimum: 512 maximum: 2048 default: 1024 height: type: integer minimum: 512 maximum: 2048 default: 768 description: For both height and width, the value must be a multiple of 32. - type: string enum: *ref_3 description: The size of the generated image. default: landscape_4_3 num_inference_steps: type: integer minimum: 1 maximum: 8 description: The number of inference steps to perform. seed: type: integer minimum: 1 description: >- The same seed and the same prompt given to the same version of the model will output the same image every time. num_images: type: number minimum: 1 maximum: 4 default: 1 description: The number of images to generate. enable_safety_checker: type: boolean default: true description: If set to True, the safety checker will be enabled. enable_prompt_expansion: type: boolean default: true description: If set to True, prompt will be upsampled with more details. acceleration: type: string enum: &ref_20 - none - regular - high default: regular description: >- The speed of the generation. The higher the speed, the faster the generation. output_format: type: string enum: &ref_21 - jpeg - png - webp default: png description: The format of the generated image. required: - model - prompt Image.v1.zImageTurboLoraPayload: type: object properties: prompt: type: string maxLength: 4000 description: >- The text prompt describing the content, style, or composition of the image to be generated. image_size: anyOf: - type: object properties: width: type: integer minimum: 512 maximum: 2048 default: 1024 height: type: integer minimum: 512 maximum: 2048 default: 768 description: For both height and width, the value must be a multiple of 32. - type: string enum: *ref_3 description: The size of the generated image. default: landscape_4_3 num_inference_steps: type: integer minimum: 1 maximum: 8 description: The number of inference steps to perform. seed: type: integer minimum: 1 description: >- The same seed and the same prompt given to the same version of the model will output the same image every time. num_images: type: number minimum: 1 maximum: 4 default: 1 description: The number of images to generate. enable_safety_checker: type: boolean default: true description: If set to True, the safety checker will be enabled. enable_prompt_expansion: type: boolean default: true description: If set to True, prompt will be upsampled with more details. acceleration: type: string enum: *ref_20 default: regular description: >- The speed of the generation. The higher the speed, the faster the generation. output_format: type: string enum: *ref_21 default: png description: The format of the generated image. model: type: string enum: - alibaba/z-image-turbo-lora loras: type: array items: type: object properties: path: type: string description: URL, HuggingFace repo ID (owner/repo). scale: type: number minimum: 0 maximum: 4 description: Scale factor for LoRA application. required: - path maxItems: 3 description: >- List of LoRA weights to apply (maximum 3). Each LoRA can be a URL, HuggingFace repo ID, or local path. required: - prompt - model Image.v1.GenerateImageResponseDTO: type: object properties: data: type: array nullable: true items: type: object properties: url: type: string nullable: true description: The URL where the file can be downloaded from. example: >- https://cdn.aimlapi.com/generations/hedgehog/1749730923700-29fe35d2-4aef-4bc5-a911-6c39884d16a8.png b64_json: type: string nullable: true description: The base64-encoded JSON of the generated image. example: null description: The list of generated images. meta: type: object nullable: true properties: usage: type: object nullable: true properties: credits_used: type: number description: The number of tokens consumed during generation. example: 120000 required: - credits_used description: Additional details about the generation. Video.v2.SubmitVideoPayload: anyOf: - type: object properties: model: type: string enum: - alibaba/wan2.1-t2v-plus prompt: type: string description: >- The text description of the scene, subject, or action to generate in the video. resolution: type: string enum: - 720P default: 720P description: >- An enumeration where the short side of the video frame determines the resolution. aspect_ratio: type: string enum: - '16:9' - '9:16' - '1:1' - '4:3' - '3:4' default: '16:9' description: The aspect ratio of the generated video. negative_prompt: type: string description: The description of elements to avoid in the generated video. watermark: type: boolean default: false description: Whether the video contains a watermark. seed: type: integer description: >- Varying the seed integer is a way to get different results for the same other request parameters. Using the same value for an identical request will produce similar results. If unspecified, a random number is chosen. enhance_prompt: type: boolean default: true description: Whether to enable prompt expansion. required: - model - prompt - type: object properties: model: type: string enum: - alibaba/wan2.1-t2v-turbo prompt: type: string description: >- The text description of the scene, subject, or action to generate in the video. resolution: type: string enum: - 480P - 720P default: 720P description: >- An enumeration where the short side of the video frame determines the resolution. aspect_ratio: type: string enum: - '16:9' - '9:16' - '1:1' - '4:3' - '3:4' default: '16:9' description: The aspect ratio of the generated video. negative_prompt: type: string description: The description of elements to avoid in the generated video. watermark: type: boolean default: false description: Whether the video contains a watermark. seed: type: integer description: >- Varying the seed integer is a way to get different results for the same other request parameters. Using the same value for an identical request will produce similar results. If unspecified, a random number is chosen. enhance_prompt: type: boolean default: true description: Whether to enable prompt expansion. required: - model - prompt - type: object properties: model: type: string enum: - alibaba/wan2.2-t2v-plus prompt: type: string description: >- The text description of the scene, subject, or action to generate in the video. resolution: type: string enum: - 480P - 1080P default: 1080P description: >- An enumeration where the short side of the video frame determines the resolution. aspect_ratio: type: string enum: - '16:9' - '9:16' - '1:1' - '4:3' - '3:4' default: '16:9' description: The aspect ratio of the generated video. negative_prompt: type: string description: The description of elements to avoid in the generated video. watermark: type: boolean default: false description: Whether the video contains a watermark. seed: type: integer description: >- Varying the seed integer is a way to get different results for the same other request parameters. Using the same value for an identical request will produce similar results. If unspecified, a random number is chosen. enhance_prompt: type: boolean default: true description: Whether to enable prompt expansion. required: - model - prompt - type: object properties: model: type: string enum: - alibaba/wan2.2-i2v-plus prompt: type: string description: >- The text description of the scene, subject, or action to generate in the video. image_url: type: string format: uri description: >- A direct link to an online image or a Base64-encoded local image that will serve as the visual base or the first frame for the video. resolution: type: string enum: - 480P - 1080P default: 1080P description: >- An enumeration where the short side of the video frame determines the resolution. negative_prompt: type: string description: The description of elements to avoid in the generated video. watermark: type: boolean default: false description: Whether the video contains a watermark. seed: type: integer description: >- Varying the seed integer is a way to get different results for the same other request parameters. Using the same value for an identical request will produce similar results. If unspecified, a random number is chosen. enhance_prompt: type: boolean default: true description: Whether to enable prompt expansion. required: - model - image_url - type: object properties: model: type: string enum: - kling-video/v1.6/standard/multi-image-to-video type: type: string enum: - multi-image-to-video image_list: type: array items: type: string format: uri minItems: 2 maxItems: 4 description: >- Array of image URLs (2-10 images) for multi-image-to-video generation aspect_ratio: type: string enum: - '16:9' - '9:16' - '1:1' default: '16:9' description: The aspect ratio of the generated video. negative_prompt: type: string description: The description of elements to avoid in the generated video. duration: type: integer description: The length of the output video in seconds. enum: &ref_22 - 5 - 10 external_task_id: type: string description: Customized Task ID prompt: type: string description: >- The text description of the scene, subject, or action to generate in the video. required: - model - image_list - type: object properties: model: type: string enum: - klingai/kling-video-v1.6-pro-effects - klingai/kling-video-v1.6-standard-effects type: type: string enum: - effects effect_scene: type: string enum: - magic_fireball - pet_moto_rider - media_interview - pet_lion - pet_delivery - pet_chef - santa_gifts - santa_hug - girlfriend - boyfriend - heart_gesture_1 - pet_wizard - smoke_smoke - thumbs_up - instant_kid - dollar_rain - cry_cry - building_collapse - gun_shot - mushroom - double_gun - pet_warrior - lightning_power - jesus_hug - shark_alert - long_hair - lie_flat - polar_bear_hug - brown_bear_hug - jazz_jazz - office_escape_plow - fly_fly - watermelon_bomb - pet_dance - boss_coming - wool_curly - iron_warrior - pet_bee - marry_me - swing_swing - day_to_night - piggy_morph - wig_out - car_explosion - ski_ski - tiger_hug - siblings - construction_worker - let's_ride - snatched - magic_broom - felt_felt - jumpdrop - celebration - splashsplash - hula - surfsurf - fairy_wing - angel_wing - dark_wing - skateskate - plushcut - jelly_press - jelly_slice - jelly_squish - jelly_jiggle - pixelpixel - yearbook - instant_film - anime_figure - rocketrocket - bloombloom - dizzydizzy - fuzzyfuzzy - squish - expansion - hug - kiss - heart_gesture - fight description: Video effect scene type image_url: anyOf: - type: string format: uri - type: array items: type: string format: uri description: >- For hug, kiss, and heart_gesture effects, pass an array containing exactly two image URLs. For squish or expansion, only one image URL is required. duration: type: integer description: The length of the output video in seconds. enum: *ref_22 required: - model - effect_scene - image_url - type: object properties: model: type: string enum: - kling-video/v1/standard/image-to-video - kling-video/v1/pro/image-to-video - kling-video/v1.5/standard/image-to-video - kling-video/v1.5/pro/image-to-video - kling-video/v1.6/pro/image-to-video image_url: type: string description: >- A direct link to an online image or a Base64-encoded local image that will serve as the visual base or the first frame for the video. prompt: type: string description: >- The text description of the scene, subject, or action to generate in the video. type: type: string enum: - image-to-video tail_image_url: type: string description: >- A direct link to an online image or a Base64-encoded local image to be used as the last frame of the video. static_mask: type: string description: >- URL of the image for Static Brush Application Area (Mask image created by users using the motion brush). dynamic_masks: type: array items: type: object properties: mask: type: string trajectories: type: array items: type: object properties: x: type: integer 'y': type: integer required: - x - 'y' minItems: 2 maxItems: 77 required: - mask - trajectories maxItems: 6 description: List of dynamic masks. camera_control: type: object properties: type: type: string enum: &ref_23 - simple - down_back - forward_up - right_turn_forward - left_turn_forward config: type: object properties: horizontal: type: number minimum: -10 maximum: 10 vertical: type: number minimum: -10 maximum: 10 pan: type: number minimum: -10 maximum: 10 tilt: type: number minimum: -10 maximum: 10 roll: type: number minimum: -10 maximum: 10 zoom: type: number minimum: -10 maximum: 10 description: Advanced camera control parameters. negative_prompt: type: string description: The description of elements to avoid in the generated video. duration: type: integer description: The length of the output video in seconds. enum: *ref_22 cfg_scale: type: number minimum: 0 maximum: 1 default: 0.5 description: >- The CFG (Classifier Free Guidance) scale is a measure of how close you want the model to stick to your prompt. external_task_id: type: string description: Customized Task ID required: - model - image_url - type: object properties: model: type: string enum: - klingai/v2-master-image-to-video - kling-video/v2.1/standard/image-to-video - klingai/v2.1-master-image-to-video - kling-video/v2.1/pro/image-to-video image_url: type: string description: >- A direct link to an online image or a Base64-encoded local image that will serve as the visual base or the first frame for the video. prompt: type: string description: >- The text description of the scene, subject, or action to generate in the video. type: type: string enum: - image-to-video static_mask: type: string description: >- URL of the image for Static Brush Application Area (Mask image created by users using the motion brush). dynamic_masks: type: array items: type: object properties: mask: type: string trajectories: type: array items: type: object properties: x: type: integer 'y': type: integer required: - x - 'y' minItems: 2 maxItems: 77 required: - mask - trajectories maxItems: 6 description: List of dynamic masks. camera_control: type: object properties: type: type: string enum: *ref_23 config: type: object properties: horizontal: type: number minimum: -10 maximum: 10 vertical: type: number minimum: -10 maximum: 10 pan: type: number minimum: -10 maximum: 10 tilt: type: number minimum: -10 maximum: 10 roll: type: number minimum: -10 maximum: 10 zoom: type: number minimum: -10 maximum: 10 description: Advanced camera control parameters. negative_prompt: type: string description: The description of elements to avoid in the generated video. duration: type: integer description: The length of the output video in seconds. enum: *ref_22 cfg_scale: type: number minimum: 0 maximum: 1 default: 0.5 description: >- The CFG (Classifier Free Guidance) scale is a measure of how close you want the model to stick to your prompt. external_task_id: type: string description: Customized Task ID required: - model - image_url - type: object properties: model: type: string enum: - kling-video/v1/standard/text-to-video - kling-video/v1/pro/text-to-video - kling-video/v1.5/pro/text-to-video - kling-video/v1.6/pro/text-to-video - klingai/v2-master-text-to-video - klingai/v2.1-master-text-to-video type: type: string enum: - text-to-video aspect_ratio: type: string enum: - '16:9' - '9:16' - '1:1' default: '16:9' description: The aspect ratio of the generated video. camera_control: type: object properties: type: type: string enum: *ref_23 config: type: object properties: horizontal: type: number minimum: -10 maximum: 10 vertical: type: number minimum: -10 maximum: 10 pan: type: number minimum: -10 maximum: 10 tilt: type: number minimum: -10 maximum: 10 roll: type: number minimum: -10 maximum: 10 zoom: type: number minimum: -10 maximum: 10 description: Camera control parameters. prompt: type: string description: >- The text description of the scene, subject, or action to generate in the video. negative_prompt: type: string description: The description of elements to avoid in the generated video. duration: type: integer description: The length of the output video in seconds. enum: *ref_22 cfg_scale: type: number minimum: 0 maximum: 1 default: 0.5 description: >- The CFG (Classifier Free Guidance) scale is a measure of how close you want the model to stick to your prompt. external_task_id: type: string description: Customized Task ID required: - model - prompt - $ref: '#/components/schemas/Kling.v2.klingV16StandardImageToVideo' - $ref: '#/components/schemas/Kling.v2.klingTextToVideoPayload' - type: object properties: model: type: string enum: - klingai/v2.5-turbo/pro/image-to-video image_url: type: string format: uri description: >- A direct link to an online image or a Base64-encoded local image that will serve as the visual base or the first frame for the video. prompt: type: string description: >- The text description of the scene, subject, or action to generate in the video. duration: type: integer description: The length of the output video in seconds. enum: &ref_24 - 5 - 10 negative_prompt: type: string description: The description of elements to avoid in the generated video. cfg_scale: type: number minimum: 0 maximum: 1 description: >- The CFG (Classifier Free Guidance) scale is a measure of how close you want the model to stick to your prompt. required: - model - image_url - prompt - type: object properties: model: type: string enum: - klingai/v2.5-turbo/pro/text-to-video prompt: type: string description: >- The text description of the scene, subject, or action to generate in the video. duration: type: integer description: The length of the output video in seconds. enum: *ref_24 negative_prompt: type: string description: The description of elements to avoid in the generated video. cfg_scale: type: number minimum: 0 maximum: 1 description: >- The CFG (Classifier Free Guidance) scale is a measure of how close you want the model to stick to your prompt. aspect_ratio: type: string enum: &ref_25 - '16:9' - '9:16' - '1:1' description: The aspect ratio of the generated video. required: - model - prompt - type: object properties: model: type: string enum: - klingai/video-v2-6-pro-motion-control prompt: type: string description: >- The text description of the scene, subject, or action to generate in the video. image_url: type: string format: uri description: >- A direct link to an online image or a Base64-encoded local image that will serve as the visual base or the first frame for the video. video_url: type: string format: uri description: >- A HTTPS URL pointing to a video or a data URI containing a video. This video will be used as a reference during generation. character_orientation: type: string enum: - image - video default: image description: >- Generate the orientation of the characters in the video, which can be selected to match the image or the video: - image: has the same orientation as the person in the picture; At this time, the reference video duration should not exceed 10 seconds; - video: consistent with the orientation of the characters in the video; At this time, the reference video duration should not exceed 30 seconds; keep_audio: type: boolean default: true description: Whether to keep the original audio from the video. required: - model - image_url - video_url - type: object properties: model: type: string enum: - klingai/v2.5-turbo/pro/image-to-video image_url: type: string format: uri description: >- A direct link to an online image or a Base64-encoded local image that will serve as the visual base or the first frame for the video. prompt: type: string description: >- The text description of the scene, subject, or action to generate in the video. duration: type: integer description: The length of the output video in seconds. enum: *ref_24 negative_prompt: type: string description: The description of elements to avoid in the generated video. cfg_scale: type: number minimum: 0 maximum: 1 description: >- The CFG (Classifier Free Guidance) scale is a measure of how close you want the model to stick to your prompt. required: - model - image_url - prompt - type: object properties: model: type: string enum: - klingai/v2.5-turbo/pro/text-to-video prompt: type: string description: >- The text description of the scene, subject, or action to generate in the video. duration: type: integer description: The length of the output video in seconds. enum: *ref_24 negative_prompt: type: string description: The description of elements to avoid in the generated video. cfg_scale: type: number minimum: 0 maximum: 1 description: >- The CFG (Classifier Free Guidance) scale is a measure of how close you want the model to stick to your prompt. aspect_ratio: type: string enum: *ref_25 description: The aspect ratio of the generated video. required: - model - prompt - type: object properties: model: type: string enum: - video-01-live2d prompt: type: string maxLength: 2000 description: >- The text description of the scene, subject, or action to generate in the video. image_url: type: string format: uri description: >- A direct link to an online image or a Base64-encoded local image that will serve as the first frame for the video. Image specifications: - format must be JPG, JPEG, or PNG; - aspect ratio should be greater than 2:5 and less than 5:2; - the shorter side must exceed 300 pixels; - file size must not exceed 20MB. enhance_prompt: type: boolean default: true description: >- If True, the incoming prompt will be automatically optimized to improve generation quality when needed. For more precise control, set it to False — the model will then follow the instructions more strictly. required: - model - prompt - image_url - type: object properties: model: type: string enum: - video-01 prompt: type: string maxLength: 2000 description: >- The text description of the scene, subject, or action to generate in the video. image_url: type: string format: uri description: >- A direct link to an online image or a Base64-encoded local image that will serve as the first frame for the video. Image specifications: - format must be JPG, JPEG, or PNG; - aspect ratio should be greater than 2:5 and less than 5:2; - the shorter side must exceed 300 pixels; - file size must not exceed 20MB. enhance_prompt: type: boolean default: true description: >- If True, the incoming prompt will be automatically optimized to improve generation quality when needed. For more precise control, set it to False — the model will then follow the instructions more strictly. required: - model - prompt - type: object properties: model: type: string enum: - minimax/hailuo-02 prompt: type: string maxLength: 2000 description: >- The text description of the scene, subject, or action to generate in the video. image_url: type: string format: uri description: >- A direct link to an online image or a Base64-encoded local image that will serve as the first frame for the video. Image specifications: - format must be JPG, JPEG, or PNG; - aspect ratio should be greater than 2:5 and less than 5:2; - the shorter side must exceed 300 pixels; - file size must not exceed 20MB. last_image_url: type: string format: uri description: >- A direct link to an online image or a Base64-encoded local image to be used as the last frame of the video. duration: type: integer description: The length of the output video in seconds. enum: - 6 - 10 resolution: type: string enum: - 768P - 1080P default: 768P description: >- The dimensions of the video display. 1080p corresponds to 1920 x 1080 pixels, 768p corresponds to 1366 x 768 pixels. enhance_prompt: type: boolean default: true description: >- If True, the incoming prompt will be automatically optimized to improve generation quality when needed. For more precise control, set it to False — the model will then follow the instructions more strictly. required: - model - prompt - type: object properties: model: type: string enum: - minimax/hailuo-2.3 prompt: type: string maxLength: 2000 description: >- The text description of the scene, subject, or action to generate in the video. image_url: type: string format: uri description: >- A direct link to an online image or a Base64-encoded local image that will serve as the first frame for the video. Image specifications: - format must be JPG, JPEG, or PNG; - aspect ratio should be greater than 2:5 and less than 5:2; - the shorter side must exceed 300 pixels; - file size must not exceed 20MB. duration: type: integer description: The length of the output video in seconds. enum: - 6 - 10 resolution: type: string enum: - 768P - 1080P default: 768P description: >- The dimensions of the video display. 1080p corresponds to 1920 x 1080 pixels, 768p corresponds to 1366 x 768 pixels. enhance_prompt: type: boolean default: true description: >- If True, the incoming prompt will be automatically optimized to improve generation quality when needed. For more precise control, set it to False — the model will then follow the instructions more strictly. required: - model - prompt - type: object properties: model: type: string enum: - minimax/hailuo-2.3-fast prompt: type: string maxLength: 2000 description: >- The text description of the scene, subject, or action to generate in the video. image_url: type: string format: uri description: >- A direct link to an online image or a Base64-encoded local image that will serve as the first frame for the video. Image specifications: - format must be JPG, JPEG, or PNG; - aspect ratio should be greater than 2:5 and less than 5:2; - the shorter side must exceed 300 pixels; - file size must not exceed 20MB. duration: type: integer description: The length of the output video in seconds. enum: - 6 - 10 resolution: type: string enum: - 768P - 1080P default: 768P description: >- The dimensions of the video display. 1080p corresponds to 1920 x 1080 pixels, 768p corresponds to 1366 x 768 pixels. enhance_prompt: type: boolean default: true description: >- If True, the incoming prompt will be automatically optimized to improve generation quality when needed. For more precise control, set it to False — the model will then follow the instructions more strictly. required: - model - prompt - image_url - type: object properties: model: type: string enum: - gen3a_turbo prompt: type: string maxLength: 1000 description: >- The text description of the scene, subject, or action to generate in the video. image_url: type: string format: uri description: >- A HTTPS URL or data URI containing an encoded image to be used as the first frame of the generated video. tail_image_url: type: string format: uri description: >- A HTTPS URL or data URI containing an encoded image to be used as the last frame of the generated video. duration: type: integer description: The length of the output video in seconds. enum: &ref_26 - 5 - 10 aspect_ratio: type: string enum: - '16:9' - '9:16' default: '16:9' description: The aspect ratio of the generated video. seed: type: integer minimum: 0 maximum: 4294967295 description: >- Varying the seed integer is a way to get different results for the same other request parameters. Using the same value for an identical request will produce similar results. If unspecified, a random number is chosen. required: - model - image_url - type: object properties: model: type: string enum: - runway/gen4_turbo prompt: type: string maxLength: 1000 description: >- The text description of the scene, subject, or action to generate in the video. image_url: type: string format: uri description: >- A HTTPS URL or data URI containing an encoded image to be used as the first frame of the generated video. duration: type: integer description: The length of the output video in seconds. enum: *ref_26 aspect_ratio: type: string enum: - '16:9' - '9:16' - '4:3' - '3:4' - '1:1' - '21:9' default: '16:9' description: The aspect ratio of the generated video. seed: type: integer minimum: 0 maximum: 4294967295 description: >- Varying the seed integer is a way to get different results for the same other request parameters. Using the same value for an identical request will produce similar results. If unspecified, a random number is chosen. required: - model - image_url - type: object properties: model: type: string enum: - runway/gen4_aleph video_url: type: string format: uri description: >- A HTTPS URL pointing to a video or a data URI containing a video. This video will be used as a reference during generation. prompt: type: string maxLength: 1000 description: >- The text description of the scene, subject, or action to generate in the video. duration: type: number enum: - 5 default: 5 description: The length of the output video in seconds. frame_size: type: string enum: &ref_27 - '1280:720' - '720:1280' - '1104:832' - '832:1104' - '960:960' - '1584:672' - '848:480' - '640:480' default: '1280:720' description: The width and height of the video. seed: type: integer minimum: 0 maximum: 4294967295 description: >- Varying the seed integer is a way to get different results for the same other request parameters. Using the same value for an identical request will produce similar results. If unspecified, a random number is chosen. references: type: array items: type: object properties: type: type: string enum: - image url: type: string format: uri required: - type - url description: >- Passing an image reference allows the model to emulate the style or content of the reference in the output. required: - model - video_url - prompt - type: object properties: model: type: string enum: - runway/act_two character: oneOf: - type: object properties: type: type: string enum: - video url: type: string format: uri required: - type - url description: >- A video of your character. In the output, the character will use the reference video performance in its original animated environment and some of the character's own movements. - type: object properties: type: type: string enum: - image url: type: string format: uri required: - type - url description: >- An image of your character. In the output, the character will use the reference video performance in its original static environment. description: >- The character to control. You can either provide a video or an image. A visually recognizable face must be visible and stay within the frame. reference: type: object properties: type: type: string enum: - video url: type: string format: uri required: - type - url description: >- Passing a video reference allows the model to emulate the style or content of the reference in the output. frame_size: type: string enum: *ref_27 default: '1280:720' description: The width and height of the video. body_control: type: boolean description: >- A boolean indicating whether to enable body control. When enabled, non-facial movements and gestures will be applied to the character in addition to facial expressions. expression_intensity: type: integer minimum: 1 maximum: 5 default: 3 description: >- An integer between 1 and 5 (inclusive). A larger value increases the intensity of the character's expression. seed: type: integer minimum: 0 maximum: 4294967295 description: >- Varying the seed integer is a way to get different results for the same other request parameters. Using the same value for an identical request will produce similar results. If unspecified, a random number is chosen. required: - model - character - reference - type: object properties: model: type: string enum: - bytedance/seedance-1-0-lite-t2v prompt: type: string description: >- The text description of the scene, subject, or action to generate in the video. resolution: type: string enum: &ref_28 - 480p - 720p default: 720p description: >- An enumeration where the short side of the video frame determines the resolution. aspect_ratio: type: string enum: &ref_29 - '16:9' - '4:3' - '1:1' - '3:4' - '9:16' default: '16:9' description: The aspect ratio of the generated video. duration: type: integer description: The length of the output video in seconds. enum: &ref_30 - 5 - 10 seed: type: integer description: >- Varying the seed integer is a way to get different results for the same other request parameters. Using the same value for an identical request will produce similar results. If unspecified, a random number is chosen. camera_fixed: type: boolean default: false description: >- Whether to fix the camera position. - true: Fix the camera position. The platform will append instructions to fix the camera position in the user's prompt, but the actual effect is not guaranteed. - false: Do not fix the camera position. watermark: type: boolean default: false description: Whether the video contains a watermark. deprecated: true required: - model - prompt - type: object properties: model: type: string enum: - bytedance/seedance-1-0-pro-t2v prompt: type: string description: >- The text description of the scene, subject, or action to generate in the video. resolution: type: string enum: *ref_28 default: 720p description: >- An enumeration where the short side of the video frame determines the resolution. aspect_ratio: type: string enum: *ref_29 default: '16:9' description: The aspect ratio of the generated video. duration: type: integer description: The length of the output video in seconds. enum: *ref_30 seed: type: integer description: >- Varying the seed integer is a way to get different results for the same other request parameters. Using the same value for an identical request will produce similar results. If unspecified, a random number is chosen. camera_fixed: type: boolean default: false description: >- Whether to fix the camera position. - true: Fix the camera position. The platform will append instructions to fix the camera position in the user's prompt, but the actual effect is not guaranteed. - false: Do not fix the camera position. watermark: type: boolean default: false description: Whether the video contains a watermark. deprecated: true required: - model - prompt - type: object properties: model: type: string enum: - bytedance/seedance-1-0-lite-i2v image_url: type: string format: uri description: >- A direct link to an online image or a Base64-encoded local image that will serve as the visual base or the first frame for the video. prompt: type: string description: >- The text description of the scene, subject, or action to generate in the video. resolution: type: string enum: *ref_28 default: 720p description: >- An enumeration where the short side of the video frame determines the resolution. duration: type: integer description: The length of the output video in seconds. enum: *ref_30 seed: type: integer description: >- Varying the seed integer is a way to get different results for the same other request parameters. Using the same value for an identical request will produce similar results. If unspecified, a random number is chosen. camera_fixed: type: boolean default: false description: >- Whether to fix the camera position. - true: Fix the camera position. The platform will append instructions to fix the camera position in the user's prompt, but the actual effect is not guaranteed. - false: Do not fix the camera position. watermark: type: boolean default: false description: Whether the video contains a watermark. deprecated: true required: - model - image_url - prompt - type: object properties: model: type: string enum: - bytedance/seedance-1-0-pro-i2v image_url: type: string format: uri description: >- A direct link to an online image or a Base64-encoded local image that will serve as the visual base or the first frame for the video. prompt: type: string description: >- The text description of the scene, subject, or action to generate in the video. resolution: type: string enum: *ref_28 default: 720p description: >- An enumeration where the short side of the video frame determines the resolution. duration: type: integer description: The length of the output video in seconds. enum: *ref_30 seed: type: integer description: >- Varying the seed integer is a way to get different results for the same other request parameters. Using the same value for an identical request will produce similar results. If unspecified, a random number is chosen. camera_fixed: type: boolean default: false description: >- Whether to fix the camera position. - true: Fix the camera position. The platform will append instructions to fix the camera position in the user's prompt, but the actual effect is not guaranteed. - false: Do not fix the camera position. watermark: type: boolean default: false description: Whether the video contains a watermark. deprecated: true required: - model - image_url - prompt - type: object properties: model: type: string enum: - bytedance/seedance-1-0-pro-fast image_url: type: string format: uri description: >- A direct link to an online image or a Base64-encoded local image that will serve as the visual base or the first frame for the video. prompt: type: string description: >- The text description of the scene, subject, or action to generate in the video. resolution: type: string enum: *ref_28 default: 720p description: >- An enumeration where the short side of the video frame determines the resolution. aspect_ratio: type: string enum: *ref_29 default: '16:9' description: The aspect ratio of the generated video. duration: type: integer description: The length of the output video in seconds. enum: *ref_30 seed: type: integer description: >- Varying the seed integer is a way to get different results for the same other request parameters. Using the same value for an identical request will produce similar results. If unspecified, a random number is chosen. camera_fixed: type: boolean default: false description: >- Whether to fix the camera position. - true: Fix the camera position. The platform will append instructions to fix the camera position in the user's prompt, but the actual effect is not guaranteed. - false: Do not fix the camera position. required: - model - prompt - $ref: '#/components/schemas/Pixverse.v2.pixverseTransition' - $ref: '#/components/schemas/Pixverse.v2.pixverseImageToVideo' - $ref: '#/components/schemas/Pixverse.v2.pixverseTextToVideo' - $ref: '#/components/schemas/Pixverse.v2.pixverseV55TextToVideo' - $ref: '#/components/schemas/Pixverse.v2.pixverseV55ImageToVideo' - type: object properties: model: type: string enum: - alibaba/wan2.5-t2v-preview prompt: type: string minLength: 1 maxLength: 800 description: >- The text description of the scene, subject, or action to generate in the video. aspect_ratio: type: string enum: - '16:9' - '9:16' - '1:1' default: '16:9' description: The aspect ratio of the generated video. resolution: type: string enum: - 480p - 720p - 1080p default: 720p description: >- An enumeration where the short side of the video frame determines the resolution. duration: type: integer description: The length of the output video in seconds. enum: - 5 - 10 negative_prompt: type: string description: The description of elements to avoid in the generated video. enable_prompt_expansion: type: boolean default: true description: Whether to enable prompt expansion. seed: type: integer description: >- Varying the seed integer is a way to get different results for the same other request parameters. Using the same value for an identical request will produce similar results. If unspecified, a random number is chosen. required: - model - prompt - type: object properties: model: type: string enum: - alibaba/wan2.5-i2v-preview prompt: type: string minLength: 1 maxLength: 800 description: >- The text description of the scene, subject, or action to generate in the video. image_url: type: string format: uri description: >- A direct link to an online image or a Base64-encoded local image that will serve as the visual base or the first frame for the video. resolution: type: string enum: - 480p - 720p - 1080p default: 720p description: >- An enumeration where the short side of the video frame determines the resolution. duration: type: integer description: The length of the output video in seconds. enum: - 5 - 10 negative_prompt: type: string description: The description of elements to avoid in the generated video. enable_prompt_expansion: type: boolean default: true description: Whether to enable prompt expansion. seed: type: integer description: >- Varying the seed integer is a way to get different results for the same other request parameters. Using the same value for an identical request will produce similar results. If unspecified, a random number is chosen. required: - model - prompt - image_url - type: object properties: model: type: string enum: - alibaba/wan-2-6-t2v prompt: type: string minLength: 1 maxLength: 800 description: >- The text description of the scene, subject, or action to generate in the video. audio_url: type: string format: uri description: >- The URL of the audio file. The model will use this audio to generate the video. aspect_ratio: type: string enum: - '16:9' - '9:16' - '1:1' - '4:3' - '3:4' default: '16:9' description: The aspect ratio of the generated video. resolution: type: string enum: &ref_31 - 720p - 1080p default: 1080p description: >- An enumeration where the short side of the video frame determines the resolution. duration: type: integer description: The length of the output video in seconds. enum: &ref_32 - 5 - 10 - 15 shot_type: type: string enum: &ref_33 - single - multi default: single description: >- Specifies the shot type of the generated video, that is, whether the video consists of a single continuous shot or multiple switched shots. This parameter takes effect only when "prompt_extend" is set to 'true':. - single: (default) Outputs a single-shot video. - multi: Outputs a multi-shot video. generate_audio: type: boolean default: true description: >- Specifies whether to automatically add audio to the generated video. This parameter takes effect only when 'audio_url' is not provided. negative_prompt: type: string description: The description of elements to avoid in the generated video. enable_prompt_expansion: type: boolean default: true description: Whether to enable prompt expansion. seed: type: integer description: >- Varying the seed integer is a way to get different results for the same other request parameters. Using the same value for an identical request will produce similar results. If unspecified, a random number is chosen. required: - model - prompt - type: object properties: model: type: string enum: - alibaba/wan-2-6-i2v image_url: type: string format: uri description: >- A direct link to an online image or a Base64-encoded local image that will serve as the visual base or the first frame for the video. prompt: type: string minLength: 1 maxLength: 800 description: >- The text description of the scene, subject, or action to generate in the video. audio_url: type: string format: uri description: >- The URL of the audio file. The model will use this audio to generate the video. resolution: type: string enum: *ref_31 default: 1080p description: >- An enumeration where the short side of the video frame determines the resolution. duration: type: integer description: The length of the output video in seconds. enum: *ref_32 shot_type: type: string enum: *ref_33 default: single description: >- Specifies the shot type of the generated video, that is, whether the video consists of a single continuous shot or multiple switched shots. This parameter takes effect only when "prompt_extend" is set to 'true':. - single: (default) Outputs a single-shot video. - multi: Outputs a multi-shot video. generate_audio: type: boolean default: true description: >- Specifies whether to automatically add audio to the generated video. This parameter takes effect only when 'audio_url' is not provided. negative_prompt: type: string description: The description of elements to avoid in the generated video. enable_prompt_expansion: type: boolean default: true description: Whether to enable prompt expansion. seed: type: integer description: >- Varying the seed integer is a way to get different results for the same other request parameters. Using the same value for an identical request will produce similar results. If unspecified, a random number is chosen. required: - model - image_url - prompt - type: object properties: model: type: string enum: - alibaba/wan-2-6-image-to-video-flash prompt: type: string minLength: 1 maxLength: 800 description: >- The text description of the scene, subject, or action to generate in the video. image_url: type: string format: uri description: >- A direct link to an online image or a Base64-encoded local image that will serve as the visual base or the first frame for the video. audio_url: type: string format: uri description: >- The URL of the audio file. The model will use this audio to generate the video. resolution: type: string enum: - 720p - 1080p default: 720p description: >- An enumeration where the short side of the video frame determines the resolution. duration: type: integer description: >- Duration of the generated video in seconds (up to 15 seconds for Flash model). enum: - 5 - 10 - 15 negative_prompt: type: string description: The description of elements to avoid in the generated video. enable_prompt_expansion: type: boolean default: true description: Whether to enable prompt expansion. seed: type: integer description: >- Varying the seed integer is a way to get different results for the same other request parameters. Using the same value for an identical request will produce similar results. If unspecified, a random number is chosen. shot_type: type: string enum: - single - multi default: single description: >- Specifies the shot type of the generated video, that is, whether the video consists of a single continuous shot or multiple switched shots. This parameter takes effect only when "prompt_extend" is set to 'true': - single: (default) Outputs a single-shot video. - multi: Outputs a multi-shot video. generate_audio: type: boolean default: true description: >- Specifies whether to automatically add audio to the generated video. This parameter takes effect only when 'audio_url' is not provided. required: - model - image_url - type: object properties: model: type: string enum: - alibaba/wan-2-6-r2v prompt: type: string minLength: 1 maxLength: 800 description: >- The text description of the scene, subject, or action to generate in the video. video_urls: type: array items: type: string format: uri minItems: 1 maxItems: 3 description: >- An array of URLs for the uploaded reference video files. This parameter is used to extract the character's appearance and voice (if any) to generate a video that matches the reference features. Each reference video must contain only one character. For example, character1 is a little girl and character2 is an alarm clock. aspect_ratio: type: string enum: - '16:9' - '9:16' - '1:1' - '4:3' - '3:4' default: '16:9' description: The aspect ratio of the generated video. resolution: type: string enum: - 720p - 1080p default: 1080p description: >- An enumeration where the short side of the video frame determines the resolution. duration: type: integer description: The length of the output video in seconds. enum: - 5 - 10 shot_type: type: string enum: - single - multi default: single description: >- Specifies the shot type of the generated video, that is, whether the video consists of a single continuous shot or multiple switched shots. This parameter takes effect only when "prompt_extend" is set to 'true':. - single: (default) Outputs a single-shot video. - multi: Outputs a multi-shot video. negative_prompt: type: string description: The description of elements to avoid in the generated video. seed: type: integer description: >- Varying the seed integer is a way to get different results for the same other request parameters. Using the same value for an identical request will produce similar results. If unspecified, a random number is chosen. enable_prompt_expansion: type: boolean default: true description: Whether to enable prompt expansion. required: - model - prompt - video_urls - $ref: '#/components/schemas/Bytedance.v2.omnihuman' - type: object properties: model: type: string enum: - veed/fabric-1.0 image_url: type: string format: uri description: >- A direct link to an online image or a Base64-encoded local image that will serve as the visual base or the first frame for the video. audio_url: type: string format: uri description: >- Reference song, should contain music and vocals. Must be a .wav or .mp3 file longer than 15 seconds. resolution: type: string enum: - 480p - 720p description: The resolution of the generated video. required: - model - image_url - audio_url - resolution - type: object properties: model: type: string enum: - veed/fabric-1.0-fast image_url: type: string format: uri description: >- A direct link to an online image or a Base64-encoded local image that will serve as the visual base or the first frame for the video. audio_url: type: string format: uri description: >- Reference song, should contain music and vocals. Must be a .wav or .mp3 file longer than 15 seconds. resolution: type: string enum: - 480p - 720p description: The resolution of the generated video. required: - model - image_url - audio_url - resolution - type: object properties: model: type: string enum: - tencent/hunyuan-video-foley video_url: type: string format: uri description: >- A HTTPS URL pointing to a video or a data URI containing a video. This video will be used as a reference during generation. prompt: type: string description: >- The text description of the scene, subject, or action to generate in the video. negative_prompt: type: string default: noisy, harsh description: The description of elements to avoid in the generated video. guidance_scale: type: number default: 4.5 description: >- Classifier-free guidance scale. Controls prompt adherence / creativity. num_inference_steps: type: integer default: 50 description: >- Number of inference steps for sampling. Higher values give better quality but take longer. seed: type: integer description: >- Varying the seed integer is a way to get different results for the same other request parameters. Using the same value for an identical request will produce similar results. If unspecified, a random number is chosen. required: - model - video_url - $ref: '#/components/schemas/Alibaba.v2.wan22VaceDepth' - $ref: '#/components/schemas/Alibaba.v2.wan22VacePose' - $ref: '#/components/schemas/Alibaba.v2.wan22VaceInpainting' - $ref: '#/components/schemas/Alibaba.v2.wan22VaceOutpainting' - $ref: '#/components/schemas/Alibaba.v2.wan22VaceReframe' - $ref: '#/components/schemas/Alibaba.v2.wan22AnimateMove' - $ref: '#/components/schemas/Alibaba.v2.wan22AnimateReplace' - type: object properties: model: type: string enum: - google/veo-3.1-t2v prompt: type: string description: >- The text description of the scene, subject, or action to generate in the video. aspect_ratio: type: string enum: - '16:9' - '9:16' description: The aspect ratio of the generated video. duration: type: integer description: The length of the output video in seconds. enum: - 4 - 6 - 8 resolution: type: string enum: - 720p - 1080p default: 1080p negative_prompt: type: string description: The description of elements to avoid in the generated video. enhance_prompt: type: boolean default: true description: Whether to enhance the video generation. generate_audio: type: boolean default: true description: Whether to generate audio for the video. seed: type: integer description: >- Varying the seed integer is a way to get different results for the same other request parameters. Using the same value for an identical request will produce similar results. If unspecified, a random number is chosen. auto_fix: type: boolean default: true description: >- Whether to automatically attempt to fix prompts that fail content policy or other validation checks by rewriting them. required: - model - prompt - type: object properties: model: type: string enum: - google/veo-3.1-i2v prompt: type: string description: >- The text description of the scene, subject, or action to generate in the video. image_url: type: string format: uri description: >- URL of the input image to animate. Should be 720p or higher resolution. aspect_ratio: type: string enum: - '16:9' - '9:16' description: The aspect ratio of the generated video. duration: type: integer description: The length of the output video in seconds. enum: - 8 resolution: type: string enum: - 720p - 1080p default: 1080p generate_audio: type: boolean default: true description: Whether to generate audio for the video. required: - model - prompt - image_url - type: object properties: model: type: string enum: - google/veo-3.1-t2v-fast prompt: type: string description: >- The text description of the scene, subject, or action to generate in the video. aspect_ratio: type: string enum: - '16:9' - '9:16' description: The aspect ratio of the generated video. duration: type: integer description: The length of the output video in seconds. enum: - 4 - 6 - 8 resolution: type: string enum: - 720p - 1080p default: 1080p negative_prompt: type: string description: The description of elements to avoid in the generated video. enhance_prompt: type: boolean default: true description: Whether to enhance the video generation. generate_audio: type: boolean default: true description: Whether to generate audio for the video. seed: type: integer description: >- Varying the seed integer is a way to get different results for the same other request parameters. Using the same value for an identical request will produce similar results. If unspecified, a random number is chosen. auto_fix: type: boolean default: true description: >- Whether to automatically attempt to fix prompts that fail content policy or other validation checks by rewriting them. required: - model - prompt - type: object properties: model: type: string enum: - google/veo-3.1-i2v-fast prompt: type: string description: >- The text description of the scene, subject, or action to generate in the video. image_url: type: string format: uri description: >- URL of the input image to animate. Should be 720p or higher resolution. aspect_ratio: type: string enum: - '16:9' - '9:16' description: The aspect ratio of the generated video. duration: type: integer description: The length of the output video in seconds. enum: - 8 resolution: type: string enum: - 720p - 1080p default: 1080p generate_audio: type: boolean default: true description: Whether to generate audio for the video. required: - model - prompt - image_url - type: object properties: model: type: string enum: - google/veo-3.1-first-last-image-to-video-fast prompt: type: string description: >- The text description of the scene, subject, or action to generate in the video. image_url: type: string format: uri description: >- URL of the input image to animate. Should be 720p or higher resolution. last_image_url: type: string format: uri description: >- A direct link to an online image or a Base64-encoded local image to be used as the last frame of the video. aspect_ratio: type: string enum: - '16:9' - '9:16' description: The aspect ratio of the generated video. duration: type: integer description: The length of the output video in seconds. enum: - 8 resolution: type: string enum: - 720p - 1080p default: 1080p generate_audio: type: boolean default: true description: Whether to generate audio for the video. required: - model - prompt - image_url - last_image_url - type: object properties: model: type: string enum: - google/veo-3.1-first-last-image-to-video prompt: type: string description: >- The text description of the scene, subject, or action to generate in the video. image_url: type: string format: uri description: >- URL of the input image to animate. Should be 720p or higher resolution. last_image_url: type: string format: uri description: >- A direct link to an online image or a Base64-encoded local image to be used as the last frame of the video. aspect_ratio: type: string enum: - '16:9' - '9:16' description: The aspect ratio of the generated video. duration: type: integer description: The length of the output video in seconds. enum: - 8 resolution: type: string enum: - 720p - 1080p default: 1080p generate_audio: type: boolean default: true description: Whether to generate audio for the video. required: - model - prompt - image_url - last_image_url - type: object properties: model: type: string enum: - google/veo-3.1-reference-to-video prompt: type: string description: >- The text description of the scene, subject, or action to generate in the video. image_urls: type: array items: type: string format: uri description: >- URL of the input image to animate. Should be 720p or higher resolution. aspect_ratio: type: string enum: - '16:9' - '9:16' description: The aspect ratio of the generated video. duration: type: integer description: The length of the output video in seconds. enum: - 8 resolution: type: string enum: - 720p - 1080p default: 1080p generate_audio: type: boolean default: true description: Whether to generate audio for the video. required: - model - prompt - image_urls - type: object properties: model: type: string enum: - google/veo3-1-extend-video prompt: type: string description: >- The text description of the scene, subject, or action to generate in the video. video_url: type: string format: uri description: >- A HTTPS URL pointing to a video or a data URI containing a video. This video will be used as a reference during generation. aspect_ratio: type: string enum: - auto - '16:9' - '9:16' default: auto description: The aspect ratio of the generated video. duration: type: integer description: The length of the output video in seconds. enum: - 7 resolution: type: string enum: - 720p default: 720p generate_audio: type: boolean default: true description: Whether to generate audio for the video. auto_fix: type: boolean default: false description: >- Whether to automatically attempt to fix prompts that fail content policy or other validation checks by rewriting them. required: - model - prompt - video_url - type: object properties: model: type: string enum: - google/veo3-1-fast-extend-video prompt: type: string description: >- The text description of the scene, subject, or action to generate in the video. video_url: type: string format: uri description: >- A HTTPS URL pointing to a video or a data URI containing a video. This video will be used as a reference during generation. aspect_ratio: type: string enum: - auto - '16:9' - '9:16' default: auto description: The aspect ratio of the generated video. duration: type: integer description: The length of the output video in seconds. enum: - 7 resolution: type: string enum: - 720p default: 720p generate_audio: type: boolean default: true description: Whether to generate audio for the video. auto_fix: type: boolean default: false description: >- Whether to automatically attempt to fix prompts that fail content policy or other validation checks by rewriting them. required: - model - prompt - video_url - $ref: '#/components/schemas/Video.v2.kandinsky5TextToVideo' - $ref: '#/components/schemas/Video.v2.kandinsky5TextToVideoDistill' - type: object properties: model: type: string enum: - krea/krea-wan-14b/text-to-video prompt: type: string description: >- The text description of the scene, subject, or action to generate in the video. num_frames: type: integer minimum: 18 maximum: 162 default: 78 description: >- Number of frames to generate. Must be a multiple of 12 plus 6, for example 18, 30, 42, etc. enable_prompt_expansion: type: boolean default: true description: Whether to enable prompt expansion. seed: type: integer description: >- Varying the seed integer is a way to get different results for the same other request parameters. Using the same value for an identical request will produce similar results. If unspecified, a random number is chosen. required: - model - prompt - type: object properties: model: type: string enum: - krea/krea-wan-14b/video-to-video prompt: type: string description: >- The text description of the scene, subject, or action to generate in the video. video_url: type: string format: uri description: >- A HTTPS URL pointing to a video or a data URI containing a video. This video will be used as a reference during generation. strength: type: number minimum: 0 maximum: 1 default: 0.85 description: >- Denoising strength for the video-to-video generation. 0.0 preserves the original, 1.0 completely remakes the video. enable_prompt_expansion: type: boolean default: true description: Whether to enable prompt expansion. seed: type: integer description: >- Varying the seed integer is a way to get different results for the same other request parameters. Using the same value for an identical request will produce similar results. If unspecified, a random number is chosen. required: - model - prompt - video_url - type: object properties: model: type: string enum: - veo2/image-to-video prompt: type: string description: >- The text description of the scene, subject, or action to generate in the video. image_url: type: string format: uri description: >- A direct link to an online image or a Base64-encoded local image that will serve as the visual base or the first frame for the video. tail_image_url: type: string format: uri description: >- A direct link to an online image or a Base64-encoded local image to be used as the last frame of the video. aspect_ratio: type: string enum: &ref_34 - '16:9' - '9:16' description: The aspect ratio of the generated video. duration: type: integer description: The length of the output video in seconds. enum: &ref_35 - 5 - 6 - 7 - 8 negative_prompt: type: string description: The description of elements to avoid in the generated video. seed: type: integer description: >- Varying the seed integer is a way to get different results for the same other request parameters. Using the same value for an identical request will produce similar results. If unspecified, a random number is chosen. enhance_prompt: type: boolean default: true description: Whether to enhance the video generation. required: - model - prompt - image_url - type: object properties: model: type: string enum: - veo2 prompt: type: string description: >- The text description of the scene, subject, or action to generate in the video. aspect_ratio: type: string enum: *ref_34 description: The aspect ratio of the generated video. duration: type: integer description: The length of the output video in seconds. enum: *ref_35 negative_prompt: type: string description: The description of elements to avoid in the generated video. seed: type: integer description: >- Varying the seed integer is a way to get different results for the same other request parameters. Using the same value for an identical request will produce similar results. If unspecified, a random number is chosen. enhance_prompt: type: boolean default: true description: Whether to enhance the video generation. required: - model - prompt - type: object properties: model: type: string enum: - google/veo3 prompt: type: string description: >- The text description of the scene, subject, or action to generate in the video. aspect_ratio: type: string enum: *ref_34 description: The aspect ratio of the generated video. resolution: type: string enum: &ref_36 - 720P - 1080P default: 720P duration: type: integer description: The length of the output video in seconds. enum: - 4 - 6 - 8 negative_prompt: type: string description: The description of elements to avoid in the generated video. seed: type: integer description: >- Varying the seed integer is a way to get different results for the same other request parameters. Using the same value for an identical request will produce similar results. If unspecified, a random number is chosen. enhance_prompt: type: boolean default: true description: Whether to enhance the video generation. generate_audio: type: boolean default: true description: Whether to generate audio for the video. required: - model - prompt - type: object properties: model: type: string enum: - google/veo-3.0-i2v prompt: type: string description: >- The text description of the scene, subject, or action to generate in the video. image_url: type: string format: uri description: >- A direct link to an online image or a Base64-encoded local image that will serve as the visual base or the first frame for the video. aspect_ratio: type: string enum: *ref_34 description: The aspect ratio of the generated video. resolution: type: string enum: *ref_36 default: 720P duration: type: integer description: The length of the output video in seconds. enum: - 4 - 6 - 8 negative_prompt: type: string description: The description of elements to avoid in the generated video. seed: type: integer description: >- Varying the seed integer is a way to get different results for the same other request parameters. Using the same value for an identical request will produce similar results. If unspecified, a random number is chosen. enhance_prompt: type: boolean default: true description: Whether to enhance the video generation. generate_audio: type: boolean default: true description: Whether to generate audio for the video. required: - model - prompt - image_url - type: object properties: model: type: string enum: - google/veo-3.0-fast prompt: type: string description: >- The text description of the scene, subject, or action to generate in the video. aspect_ratio: type: string enum: *ref_34 description: The aspect ratio of the generated video. resolution: type: string enum: *ref_36 default: 720P duration: type: integer description: The length of the output video in seconds. enum: - 4 - 6 - 8 negative_prompt: type: string description: The description of elements to avoid in the generated video. seed: type: integer description: >- Varying the seed integer is a way to get different results for the same other request parameters. Using the same value for an identical request will produce similar results. If unspecified, a random number is chosen. enhance_prompt: type: boolean default: true description: Whether to enhance the video generation. generate_audio: type: boolean default: true description: Whether to generate audio for the video. required: - model - prompt - type: object properties: model: type: string enum: - google/veo-3.0-i2v-fast prompt: type: string description: >- The text description of the scene, subject, or action to generate in the video. image_url: type: string format: uri description: >- A direct link to an online image or a Base64-encoded local image that will serve as the visual base or the first frame for the video. aspect_ratio: type: string enum: *ref_34 description: The aspect ratio of the generated video. resolution: type: string enum: *ref_36 default: 720P duration: type: integer description: The length of the output video in seconds. enum: - 4 - 6 - 8 negative_prompt: type: string description: The description of elements to avoid in the generated video. seed: type: integer description: >- Varying the seed integer is a way to get different results for the same other request parameters. Using the same value for an identical request will produce similar results. If unspecified, a random number is chosen. enhance_prompt: type: boolean default: true description: Whether to enhance the video generation. generate_audio: type: boolean default: true description: Whether to generate audio for the video. required: - model - prompt - image_url - type: object properties: model: type: string enum: - openai/sora-2-t2v prompt: type: string description: >- The text description of the scene, subject, or action to generate in the video. duration: type: integer description: The length of the output video in seconds. enum: &ref_37 - 4 - 8 - 12 aspect_ratio: type: string enum: &ref_38 - '16:9' - '9:16' default: '16:9' description: The aspect ratio of the generated video. resolution: type: string enum: - 720p default: 720p description: >- The resolution of the output video, where the number refers to the short side in pixels. required: - model - prompt - type: object properties: model: type: string enum: - openai/sora-2-i2v image_url: type: string format: uri description: >- A URL or a Base64-encoded image file used as the initial frame for video generation. The image dimensions must match the selected video resolution and aspect ratio. Supported configurations include: 720p with aspect ratios: - 16:9 — 1280x720 - 9:16 — 720x1280 1080p with aspect ratios: - 16:9 — 1792x1024 - 9:16 — 1024x1792 prompt: type: string description: >- The text description of the scene, subject, or action to generate in the video. duration: type: integer description: The length of the output video in seconds. enum: *ref_37 aspect_ratio: type: string enum: *ref_38 default: '16:9' description: The aspect ratio of the generated video. resolution: type: string enum: - 720p default: 720p description: >- The resolution of the output video, where the number refers to the short side in pixels. required: - model - image_url - prompt - type: object properties: model: type: string enum: - openai/sora-2-pro-t2v prompt: type: string description: >- The text description of the scene, subject, or action to generate in the video. duration: type: integer description: The length of the output video in seconds. enum: *ref_37 aspect_ratio: type: string enum: *ref_38 default: '16:9' description: The aspect ratio of the generated video. resolution: type: string enum: - 720p - 1080p default: 1080p description: >- The resolution of the output video, where the number refers to the short side in pixels. required: - model - prompt - type: object properties: model: type: string enum: - openai/sora-2-pro-i2v image_url: type: string format: uri description: >- A URL or a Base64-encoded image file used as the initial frame for video generation. The image dimensions must match the selected video resolution and aspect ratio. Supported configurations include: 720p with aspect ratios: - 16:9 — 1280x720 - 9:16 — 720x1280 1080p with aspect ratios: - 16:9 — 1792x1024 - 9:16 — 1024x1792 prompt: type: string description: >- The text description of the scene, subject, or action to generate in the video. duration: type: integer description: The length of the output video in seconds. enum: *ref_37 aspect_ratio: type: string enum: *ref_38 default: '16:9' description: The aspect ratio of the generated video. resolution: type: string enum: - 720p - 1080p default: 1080p description: >- The resolution of the output video, where the number refers to the short side in pixels. required: - model - image_url - prompt - type: object properties: model: type: string enum: - openai/sora-2-t2v prompt: type: string description: >- The text description of the scene, subject, or action to generate in the video. duration: type: integer description: The length of the output video in seconds. enum: &ref_39 - 4 - 8 - 12 aspect_ratio: type: string enum: &ref_40 - '16:9' - '9:16' default: '16:9' description: The aspect ratio of the generated video. resolution: type: string enum: - 720p default: 720p description: >- The resolution of the output video, where the number refers to the short side in pixels. required: - model - prompt - type: object properties: model: type: string enum: - openai/sora-2-i2v image_url: type: string format: uri description: >- A URL or a Base64-encoded image file used as the initial frame for video generation. The image dimensions must match the selected video resolution and aspect ratio. Supported configurations include: 720p with aspect ratios: - 16:9 — 1280x720 - 9:16 — 720x1280 1080p with aspect ratios: - 16:9 — 1792x1024 - 9:16 — 1024x1792 prompt: type: string description: >- The text description of the scene, subject, or action to generate in the video. duration: type: integer description: The length of the output video in seconds. enum: *ref_39 aspect_ratio: type: string enum: *ref_40 default: '16:9' description: The aspect ratio of the generated video. resolution: type: string enum: - 720p default: 720p description: >- The resolution of the output video, where the number refers to the short side in pixels. required: - model - image_url - prompt - type: object properties: model: type: string enum: - openai/sora-2-pro-t2v prompt: type: string description: >- The text description of the scene, subject, or action to generate in the video. duration: type: integer description: The length of the output video in seconds. enum: *ref_39 aspect_ratio: type: string enum: *ref_40 default: '16:9' description: The aspect ratio of the generated video. resolution: type: string enum: - 720p - 1080p default: 1080p description: >- The resolution of the output video, where the number refers to the short side in pixels. required: - model - prompt - type: object properties: model: type: string enum: - openai/sora-2-pro-i2v image_url: type: string format: uri description: >- A URL or a Base64-encoded image file used as the initial frame for video generation. The image dimensions must match the selected video resolution and aspect ratio. Supported configurations include: 720p with aspect ratios: - 16:9 — 1280x720 - 9:16 — 720x1280 1080p with aspect ratios: - 16:9 — 1792x1024 - 9:16 — 1024x1792 prompt: type: string description: >- The text description of the scene, subject, or action to generate in the video. duration: type: integer description: The length of the output video in seconds. enum: *ref_39 aspect_ratio: type: string enum: *ref_40 default: '16:9' description: The aspect ratio of the generated video. resolution: type: string enum: - 720p - 1080p default: 1080p description: >- The resolution of the output video, where the number refers to the short side in pixels. required: - model - image_url - prompt - type: object properties: prompt: type: string description: >- The text description of the scene, subject, or action to generate in the video. aspect_ratio: type: string enum: - '1:1' - '16:9' - '9:16' - '4:3' - '3:4' - '21:9' - '9:21' description: The aspect ratio of the generated video. loop: type: boolean default: false description: Whether to loop the video keyframes: type: object properties: frame0: anyOf: - type: object properties: type: type: string enum: - generation id: type: string description: Id of a previous generation to extend required: - type - id - type: object properties: type: type: string enum: - image url: type: string format: uri description: >- A direct link to an online image or a Base64-encoded local image that will serve as the visual base or the first frame for the video. required: - type - url frame1: anyOf: - type: object properties: type: type: string enum: - generation id: type: string description: Id of a previous generation to extend required: - type - id - type: object properties: type: type: string enum: - image url: type: string format: uri description: >- A direct link to an online image or a Base64-encoded local image that will serve as the visual base or the first frame for the video. required: - type - url description: Keyframes for image-to-video, extend, or interpolate model: type: string enum: - luma/ray-2 - luma/ray-flash-2 resolution: type: string enum: - 540p - 720p - 1080p - 4k description: >- The resolution of the output video, where the number refers to the short side in pixels. duration: type: integer description: The length of the output video in seconds. enum: - 5 - 9 required: - prompt - model additionalProperties: false - type: object properties: model: type: string enum: - klingai/avatar-standard image_url: type: string format: uri description: >- A direct link to an online image or a Base64-encoded local image that will serve as the visual base or the first frame for the video. audio_url: type: string description: >- The URL of the audio file. Supported formats: MP3, WAV, M4A, AAC. Maximum file size: 5 MB. prompt: type: string maxLength: 2500 description: >- The text description of the scene, subject, or action to generate in the video. required: - model - image_url - audio_url - type: object properties: model: type: string enum: - klingai/avatar-pro image_url: type: string format: uri description: >- A direct link to an online image or a Base64-encoded local image that will serve as the visual base or the first frame for the video. audio_url: type: string description: >- The URL of the audio file. Supported formats: MP3, WAV, M4A, AAC. Maximum file size: 5 MB. prompt: type: string maxLength: 2500 description: >- The text description of the scene, subject, or action to generate in the video. required: - model - image_url - audio_url - type: object properties: model: type: string enum: - ltxv/ltxv-2 image_url: type: string format: uri description: >- A direct link to an online image or a Base64-encoded local image that will serve as the visual base or the first frame for the video. prompt: type: string description: >- The text description of the scene, subject, or action to generate in the video. duration: type: integer description: The length of the output video in seconds. enum: - 6 - 8 - 10 resolution: type: string enum: - 1080p - 1440p - 2160p default: 1080p description: >- The resolution of the output video, where the number refers to the short side in pixels. aspect_ratio: type: string enum: - '16:9' default: '16:9' description: The aspect ratio of the generated video. fps: type: integer description: Frames per second of the generated video. enum: - 25 - 50 generate_audio: type: boolean default: true description: Whether to generate audio for the video. required: - model - prompt - type: object properties: model: type: string enum: - ltxv/ltxv-2-fast image_url: type: string format: uri description: >- A direct link to an online image or a Base64-encoded local image that will serve as the visual base or the first frame for the video. prompt: type: string description: >- The text description of the scene, subject, or action to generate in the video. duration: type: integer description: The length of the output video in seconds. enum: - 6 - 8 - 10 resolution: type: string enum: - 1080p - 1440p - 2160p default: 1080p description: >- The resolution of the output video, where the number refers to the short side in pixels. aspect_ratio: type: string enum: - '16:9' default: '16:9' description: The aspect ratio of the generated video. fps: type: integer description: Frames per second of the generated video. enum: - 25 - 50 generate_audio: type: boolean default: true description: Whether to generate audio for the video. required: - model - prompt - $ref: '#/components/schemas/Video.v2.longcatDistilled' - type: object properties: model: type: string enum: - klingai/video-o1-image-to-video prompt: type: string maxLength: 2500 description: >- The text description of the scene, subject, or action to generate in the video. image_url: type: string format: uri description: >- A direct link to an online image or a Base64-encoded local image that will serve as the visual base or the first frame for the video. last_image_url: type: string format: uri description: >- A direct link to an online image or a Base64-encoded local image to be used as the last frame of the video. duration: type: integer description: The length of the output video in seconds. enum: - 5 - 10 default: '5' required: - model - prompt - image_url - type: object properties: model: type: string enum: - klingai/video-o1-reference-to-video prompt: type: string maxLength: 2500 description: >- The text description of the scene, subject, or action to generate in the video. image_list: type: array items: type: string format: uri minItems: 1 maxItems: 7 description: Array of image URLs for multi-image-to-video generation. elements: type: array items: type: object properties: reference_image_urls: type: array items: type: string format: uri minItems: 1 maxItems: 4 description: Additional reference images from different angles. frontal_image_url: type: string format: uri description: The frontal image of the element (main view). required: - reference_image_urls - frontal_image_url maxItems: 4 description: Elements (characters/objects) to include in the video. aspect_ratio: type: string enum: - '16:9' - '9:16' - '1:1' default: '16:9' description: The aspect ratio of the generated video. duration: type: integer description: The length of the output video in seconds. enum: - 5 - 10 default: '5' required: - model - prompt - type: object properties: model: type: string enum: - klingai/video-o1-video-to-video-edit prompt: type: string maxLength: 2500 description: >- The text description of the scene, subject, or action to generate in the video. video_url: type: string format: uri description: >- A HTTPS URL pointing to a video or a data URI containing a video. This video will be used as a reference during generation. image_list: type: array items: type: string format: uri minItems: 1 maxItems: 7 description: Array of image URLs for multi-image-to-video generation. elements: type: array items: type: object properties: reference_image_urls: type: array items: type: string format: uri minItems: 1 maxItems: 4 description: Additional reference images from different angles. frontal_image_url: type: string format: uri description: The frontal image of the element (main view). required: - reference_image_urls - frontal_image_url maxItems: 4 description: Elements (characters/objects) to include in the video. keep_audio: type: boolean default: false description: Whether to keep the original audio from the video. required: - model - prompt - video_url - type: object properties: model: type: string enum: - klingai/video-o1-video-to-video-reference prompt: type: string maxLength: 2500 description: >- The text description of the scene, subject, or action to generate in the video. video_url: type: string format: uri description: >- A HTTPS URL pointing to a video or a data URI containing a video. This video will be used as a reference during generation. image_list: type: array items: type: string format: uri minItems: 1 maxItems: 4 description: Array of image URLs for multi-image-to-video generation. aspect_ratio: type: string enum: - '16:9' - '9:16' - '1:1' default: '16:9' description: The aspect ratio of the generated video. duration: type: integer description: The length of the output video in seconds. enum: - 5 - 10 default: '5' elements: type: array items: type: object properties: reference_image_urls: type: array items: type: string format: uri minItems: 1 maxItems: 4 description: Additional reference images from different angles. frontal_image_url: type: string format: uri description: The frontal image of the element (main view). required: - reference_image_urls - frontal_image_url maxItems: 4 description: Elements (characters/objects) to include in the video. keep_audio: type: boolean default: false description: Whether to keep the original audio from the video. required: - model - prompt - video_url - image_list - type: object properties: model: type: string enum: - klingai/video-v2-6-pro-text-to-video prompt: type: string maxLength: 2500 description: >- The text description of the scene, subject, or action to generate in the video. aspect_ratio: type: string enum: - '16:9' - '9:16' - '1:1' description: The aspect ratio of the generated video. duration: type: integer description: The length of the output video in seconds. enum: - 5 - 10 default: '5' negative_prompt: type: string description: The description of elements to avoid in the generated video. cfg_scale: type: number minimum: 0 maximum: 1 description: >- The CFG (Classifier Free Guidance) scale is a measure of how close you want the model to stick to your prompt. generate_audio: type: boolean default: true description: Whether to generate audio for the video. required: - model - prompt - type: object properties: model: type: string enum: - klingai/video-v2-6-pro-image-to-video prompt: type: string maxLength: 2500 description: >- The text description of the scene, subject, or action to generate in the video. image_url: type: string format: uri description: >- A direct link to an online image or a Base64-encoded local image that will serve as the visual base or the first frame for the video. duration: type: integer description: The length of the output video in seconds. enum: - 5 - 10 default: '5' negative_prompt: type: string description: The description of elements to avoid in the generated video. generate_audio: type: boolean default: true description: Whether to generate audio for the video. required: - model - prompt - image_url - type: object properties: prompt: type: string description: >- Text prompt for video generation. Either prompt or multi_prompt must be provided, but not both. multi_prompt: type: array items: type: string description: >- List of prompts for multi-shot video generation. If provided, overrides the single prompt and divides the video into multiple shots with specified prompts and durations. duration: type: integer description: The length of the output video in seconds. enum: &ref_41 - 3 - 4 - 5 - 6 - 7 - 8 - 9 - 10 - 11 - 12 - 13 - 14 - 15 default: '5' shot_type: type: string enum: &ref_42 - customize - intelligent default: customize description: The type of multi-shot video generation generate_audio: type: boolean default: true description: Whether to generate audio for the video. negative_prompt: type: string description: The description of elements to avoid in the generated video. cfg_scale: type: number minimum: 0 maximum: 1 description: >- The CFG (Classifier Free Guidance) scale is a measure of how close you want the model to stick to your prompt. model: type: string enum: - klingai/video-v3-standard-image-to-video - klingai/video-v3-pro-image-to-video image_url: type: string format: uri description: >- A direct link to an online image or a Base64-encoded local image that will serve as the visual base or the first frame for the video. tail_image_url: type: string format: uri description: >- A direct link to an online image or a Base64-encoded local image to be used as the last frame of the video. elements: type: array items: type: object properties: reference_image_urls: type: array items: type: string format: uri minItems: 1 maxItems: 4 description: Additional reference images from different angles. frontal_image_url: type: string format: uri description: The frontal image of the element (main view). video_url: type: string format: uri description: >- The video URL of the element. A request can only have one element with a video. required: - reference_image_urls maxItems: 4 description: >- Elements (characters/objects) to include in the video. Each example can either be an image set (frontal + reference images) or a video required: - model - image_url - type: object properties: model: type: string enum: - klingai/video-v3-standard-text-to-video - klingai/video-v3-pro-text-to-video prompt: type: string description: >- Text prompt for video generation. Either prompt or multi_prompt must be provided, but not both. multi_prompt: type: array items: type: string description: >- List of prompts for multi-shot video generation. If provided, overrides the single prompt and divides the video into multiple shots with specified prompts and durations. aspect_ratio: type: string enum: - '16:9' - '9:16' - '1:1' default: '16:9' description: The aspect ratio of the generated video. duration: type: integer description: The length of the output video in seconds. enum: *ref_41 default: '5' shot_type: type: string enum: *ref_42 default: customize description: The type of multi-shot video generation generate_audio: type: boolean default: true description: Whether to generate audio for the video. negative_prompt: type: string description: The description of elements to avoid in the generated video. cfg_scale: type: number minimum: 0 maximum: 1 description: >- The CFG (Classifier Free Guidance) scale is a measure of how close you want the model to stick to your prompt. required: - model - type: object properties: model: type: string enum: - magic/text-to-video prompt: type: string template: type: string enum: - Shanghai Drone Show default: Shanghai Drone Show required: - model - prompt - type: object properties: model: type: string enum: - magic/image-to-video image_url: type: string format: uri template: type: string enum: - Thailand Street - Times Square Billboard - New York Times Square (77) - Phone Social - Art Gallery - New York Times Square (66) - Dubai Museum - Digital Float - Rotating Cards - Desktop Reveal - Egypt Pyramid - Frames Drop - Cappadocia Balloons - Times Square Round Screen - Stockholm Metro - Tokyo Billboard - San Francisco Skyscrapers - Malaysia Shop - Las Vegas LED - Phone App - Paris Eiffel Tower default: Thailand Street required: - model - image_url - type: object properties: model: type: string enum: - magic/video-to-video video_url: type: string format: uri template: type: string enum: - Thailand Street - Times Square Billboard - New York Times Square (78) - Phone Social - Art Gallery - New York Times Square (67) - Dubai Museum - Rotating Cards - Desktop Reveal - Egypt Pyramid - Cappadocia Balloons - Times Square Round Screen - Stockholm Metro - Tokyo Billboard - San Francisco Skyscrapers - Malaysia Shop - Las Vegas LED - Phone App - Paris Eiffel Tower default: Thailand Street required: - model - video_url Kling.v2.klingV16StandardImageToVideo: type: object properties: model: type: string enum: - kling-video/v1.6/standard/image-to-video image_url: type: string format: uri description: >- A direct link to an online image or a Base64-encoded local image that will serve as the visual base or the first frame for the video. ratio: type: string enum: - '16:9' - '9:16' - '1:1' deprecated: true aspect_ratio: type: string enum: - '16:9' - '9:16' - '1:1' deprecated: true prompt: type: string description: >- The text description of the scene, subject, or action to generate in the video. duration: type: integer description: The length of the output video in seconds. enum: &ref_43 - 5 - 10 negative_prompt: type: string description: The description of elements to avoid in the generated video. cfg_scale: type: number minimum: 0 maximum: 1 description: >- The CFG (Classifier Free Guidance) scale is a measure of how close you want the model to stick to your prompt. required: - model - image_url - prompt Kling.v2.klingTextToVideoPayload: type: object properties: model: type: string enum: - kling-video/v1.6/standard/text-to-video ratio: type: string enum: - '16:9' - '9:16' - '1:1' deprecated: true aspect_ratio: type: string enum: - '16:9' - '9:16' - '1:1' description: The aspect ratio of the generated video. prompt: type: string description: >- The text description of the scene, subject, or action to generate in the video. duration: type: integer description: The length of the output video in seconds. enum: *ref_43 negative_prompt: type: string description: The description of elements to avoid in the generated video. cfg_scale: type: number minimum: 0 maximum: 1 description: >- The CFG (Classifier Free Guidance) scale is a measure of how close you want the model to stick to your prompt. required: - model - prompt Pixverse.v2.pixverseTransition: type: object properties: model: type: string enum: - pixverse/v5/transition image_url: type: string format: uri description: URL of the image to be used as the first frame of the video. tail_image_url: type: string format: uri description: >- A direct link to an online image or a Base64-encoded local image to be used as the last frame of the video. prompt: type: string description: >- The text description of the scene, subject, or action to generate in the video. resolution: type: string enum: &ref_44 - 360p - 540p - 720p - 1080p default: 720p description: >- An enumeration where the short side of the video frame determines the resolution. duration: type: integer description: >- The output video length in seconds. The 1080p quality option does not support 8-second videos. enum: &ref_45 - 5 - 8 negative_prompt: type: string description: The description of elements to avoid in the generated video. style: type: string enum: &ref_46 - anime - 3d_animation - clay - comic - cyberpunk description: The style of the generated video. seed: type: integer description: >- Varying the seed integer is a way to get different results for the same other request parameters. Using the same value for an identical request will produce similar results. If unspecified, a random number is chosen. required: - model - image_url - tail_image_url - prompt Pixverse.v2.pixverseImageToVideo: type: object properties: model: type: string enum: - pixverse/v5/image-to-video image_url: type: string format: uri description: URL of the image to be used as the first frame of the video. prompt: type: string description: >- The text description of the scene, subject, or action to generate in the video. aspect_ratio: type: string enum: &ref_47 - '16:9' - '4:3' - '1:1' - '3:4' - '9:16' default: '16:9' description: The aspect ratio of the generated video. resolution: type: string enum: *ref_44 default: 720p description: >- An enumeration where the short side of the video frame determines the resolution. duration: type: integer description: >- The output video length in seconds. The 1080p quality option does not support 8-second videos. enum: *ref_45 negative_prompt: type: string description: The description of elements to avoid in the generated video. style: type: string enum: *ref_46 description: The style of the generated video. seed: type: integer description: >- Varying the seed integer is a way to get different results for the same other request parameters. Using the same value for an identical request will produce similar results. If unspecified, a random number is chosen. required: - model - image_url - prompt Pixverse.v2.pixverseTextToVideo: type: object properties: model: type: string enum: - pixverse/v5/text-to-video prompt: type: string description: >- The text description of the scene, subject, or action to generate in the video. aspect_ratio: type: string enum: *ref_47 default: '16:9' description: The aspect ratio of the generated video. resolution: type: string enum: *ref_44 default: 720p description: >- An enumeration where the short side of the video frame determines the resolution. duration: type: integer description: >- The output video length in seconds. The 1080p quality option does not support 8-second videos. enum: *ref_45 negative_prompt: type: string description: The description of elements to avoid in the generated video. style: type: string enum: *ref_46 description: The style of the generated video. seed: type: integer description: >- Varying the seed integer is a way to get different results for the same other request parameters. Using the same value for an identical request will produce similar results. If unspecified, a random number is chosen. required: - model - prompt Pixverse.v2.pixverseV55TextToVideo: type: object properties: model: type: string enum: - pixverse/v5-5-text-to-video prompt: type: string description: >- The text description of the scene, subject, or action to generate in the video. aspect_ratio: type: string enum: &ref_48 - '16:9' - '4:3' - '1:1' - '3:4' - '9:16' default: '16:9' description: The aspect ratio of the generated video. resolution: type: string enum: &ref_49 - 360p - 540p - 720p - 1080p default: 720p description: >- An enumeration where the short side of the video frame determines the resolution. duration: type: integer description: >- The output video length in seconds. The 1080p quality option does not support 8-second videos. enum: &ref_50 - 5 - 8 - 10 negative_prompt: type: string description: The description of elements to avoid in the generated video. style: type: string enum: &ref_51 - anime - 3d_animation - clay - comic - cyberpunk description: The style of the generated video. seed: type: integer description: >- Varying the seed integer is a way to get different results for the same other request parameters. Using the same value for an identical request will produce similar results. If unspecified, a random number is chosen. generate_audio_switch: type: boolean description: >- Audio switch. Controls whether the video has audio. true: Audio on, false: Audio off generate_multi_clip_switch: type: boolean description: >- Single or multi-clip switch. Controls single-clip and multi-clip generation modes. true: Multi-clip, false: Single-clip thinking_type: type: string enum: &ref_52 - enabled - disabled - auto description: >- Prompt reasoning enhancement. Controls whether the system should enhance your prompt with internal reasoning and optimization. required: - model - prompt Pixverse.v2.pixverseV55ImageToVideo: type: object properties: model: type: string enum: - pixverse/v5-5-image-to-video image_url: type: string format: uri description: URL of the image to be used as the first frame of the video. prompt: type: string description: >- The text description of the scene, subject, or action to generate in the video. aspect_ratio: type: string enum: *ref_48 default: '16:9' description: The aspect ratio of the generated video. resolution: type: string enum: *ref_49 default: 720p description: >- An enumeration where the short side of the video frame determines the resolution. duration: type: integer description: >- The output video length in seconds. The 1080p quality option does not support 8-second videos. enum: *ref_50 negative_prompt: type: string description: The description of elements to avoid in the generated video. style: type: string enum: *ref_51 description: The style of the generated video. seed: type: integer description: >- Varying the seed integer is a way to get different results for the same other request parameters. Using the same value for an identical request will produce similar results. If unspecified, a random number is chosen. generate_audio_switch: type: boolean description: >- Audio switch. Controls whether the video has audio. true: Audio on, false: Audio off generate_multi_clip_switch: type: boolean description: >- Single or multi-clip switch. Controls single-clip and multi-clip generation modes. true: Multi-clip, false: Single-clip thinking_type: type: string enum: *ref_52 description: >- Prompt reasoning enhancement. Controls whether the system should enhance your prompt with internal reasoning and optimization. required: - model - image_url - prompt Bytedance.v2.omnihuman: type: object properties: model: type: string enum: - bytedance/omnihuman - bytedance/omnihuman/v1.5 image_url: type: string format: uri description: >- A direct link to an online image or a Base64-encoded local image that will serve as the visual base or the first frame for the video. audio_url: type: string format: uri description: >- The URL of the audio file for lip-sync animation. The model detects spoken parts and syncs the character's mouth to them. Audio must be under 30s long. required: - model - image_url - audio_url Alibaba.v2.wan22VaceDepth: type: object properties: model: type: string enum: - alibaba/wan2.2-vace-fun-a14b-depth video_url: type: string format: uri description: URL to the source video file. Required for depth task prompt: type: string description: >- The text description of the scene, subject, or action to generate in the video. negative_prompt: type: string default: >- letterboxing, borders, black bars, bright colors, overexposed, static, blurred details, subtitles, style, artwork, painting, picture, still, overall gray, worst quality, low quality, JPEG compression residue, ugly, incomplete, extra fingers, poorly drawn hands, poorly drawn faces, deformed, disfigured, malformed limbs, fused fingers, still picture, cluttered background, three legs, many people in the background, walking backwards description: The description of elements to avoid in the generated video. match_input_num_frames: type: boolean num_frames: type: integer minimum: 81 maximum: 241 default: 81 description: Number of frames to generate. match_input_frames_per_second: type: boolean description: Whether to match the input video's frames per second (FPS). frames_per_second: type: integer minimum: 5 maximum: 30 default: 16 description: Frames per second of the generated video. seed: type: integer description: >- Varying the seed integer is a way to get different results for the same other request parameters. Using the same value for an identical request will produce similar results. If unspecified, a random number is chosen. resolution: type: string enum: &ref_53 - auto - 240p - 360p - 480p - 580p - 720p default: auto description: >- An enumeration where the short side of the video frame determines the resolution. aspect_ratio: type: string enum: &ref_54 - auto - '16:9' - '1:1' - '9:16' default: auto description: The aspect ratio of the generated video. num_inference_steps: type: integer default: 30 description: >- Number of inference steps for sampling. Higher values give better quality but take longer. guidance_scale: type: number default: 5 description: >- Classifier-free guidance scale. Controls prompt adherence / creativity. shift: type: number default: 5 description: Noise schedule shift parameter. Affects temporal dynamics. image_list: type: array items: type: string format: uri description: Array of image URLs for multi-image-to-video generation. image_url: type: string format: uri description: URL of the image to be used as the first frame of the video. last_image_url: type: string format: uri description: >- A direct link to an online image or a Base64-encoded local image to be used as the last frame of the video. enable_safety_checker: type: boolean description: If set to true, the safety checker will be enabled. enable_prompt_expansion: type: boolean description: Whether to enable prompt expansion. preprocess: type: boolean description: Whether to preprocess the input video. acceleration: type: string enum: &ref_55 - none - regular default: regular description: Acceleration to use for inference. video_quality: type: string enum: &ref_56 - low - medium - high - maximum default: high description: The quality of the generated video. video_write_mode: type: string enum: &ref_57 - fast - balanced - small default: balanced description: The method used to write the video. num_interpolated_frames: type: integer description: Number of frames to interpolate between the original frames. temporal_downsample_factor: type: integer description: Temporal downsample factor for the video. enable_auto_downsample: type: boolean description: The minimum frames per second to downsample the video to. auto_downsample_min_fps: type: number default: 15 description: The minimum frames per second to downsample the video to. interpolator_model: type: string enum: &ref_58 - rife - film default: film description: The model to use for interpolation. Rife, or film are available. sync_mode: type: boolean description: >- The synchronization mode for audio and video. Loose or tight are available. required: - model - video_url - prompt Alibaba.v2.wan22VacePose: type: object properties: model: type: string enum: - alibaba/wan2.2-vace-fun-a14b-pose video_url: type: string format: uri description: URL to the source video file. Required for pose task prompt: type: string description: >- The text description of the scene, subject, or action to generate in the video. negative_prompt: type: string default: >- letterboxing, borders, black bars, bright colors, overexposed, static, blurred details, subtitles, style, artwork, painting, picture, still, overall gray, worst quality, low quality, JPEG compression residue, ugly, incomplete, extra fingers, poorly drawn hands, poorly drawn faces, deformed, disfigured, malformed limbs, fused fingers, still picture, cluttered background, three legs, many people in the background, walking backwards description: The description of elements to avoid in the generated video. match_input_num_frames: type: boolean num_frames: type: integer minimum: 81 maximum: 241 default: 81 description: Number of frames to generate. match_input_frames_per_second: type: boolean description: Whether to match the input video's frames per second (FPS). frames_per_second: type: integer minimum: 5 maximum: 30 default: 16 description: Frames per second of the generated video. seed: type: integer description: >- Varying the seed integer is a way to get different results for the same other request parameters. Using the same value for an identical request will produce similar results. If unspecified, a random number is chosen. resolution: type: string enum: *ref_53 default: auto description: >- An enumeration where the short side of the video frame determines the resolution. aspect_ratio: type: string enum: *ref_54 default: auto description: The aspect ratio of the generated video. num_inference_steps: type: integer default: 30 description: >- Number of inference steps for sampling. Higher values give better quality but take longer. guidance_scale: type: number default: 5 description: >- Classifier-free guidance scale. Controls prompt adherence / creativity. shift: type: number default: 5 description: Noise schedule shift parameter. Affects temporal dynamics. image_list: type: array items: type: string format: uri description: Array of image URLs for multi-image-to-video generation. image_url: type: string format: uri description: URL of the image to be used as the first frame of the video. last_image_url: type: string format: uri description: >- A direct link to an online image or a Base64-encoded local image to be used as the last frame of the video. enable_safety_checker: type: boolean description: If set to true, the safety checker will be enabled. enable_prompt_expansion: type: boolean description: Whether to enable prompt expansion. preprocess: type: boolean description: Whether to preprocess the input video. acceleration: type: string enum: *ref_55 default: regular description: Acceleration to use for inference. video_quality: type: string enum: *ref_56 default: high description: The quality of the generated video. video_write_mode: type: string enum: *ref_57 default: balanced description: The method used to write the video. num_interpolated_frames: type: integer description: Number of frames to interpolate between the original frames. temporal_downsample_factor: type: integer description: Temporal downsample factor for the video. enable_auto_downsample: type: boolean description: The minimum frames per second to downsample the video to. auto_downsample_min_fps: type: number default: 15 description: The minimum frames per second to downsample the video to. interpolator_model: type: string enum: *ref_58 default: film description: The model to use for interpolation. Rife, or film are available. sync_mode: type: boolean description: >- The synchronization mode for audio and video. Loose or tight are available. required: - model - video_url - prompt Alibaba.v2.wan22VaceInpainting: type: object properties: model: type: string enum: - alibaba/wan2.2-vace-fun-a14b-inpainting video_url: type: string format: uri description: URL to the source video file. Required for inpainting mask_video_url: type: string format: uri description: URL to the source mask file. Required for inpainting mask_image_url: type: string format: uri description: >- URL to the guiding mask file. If provided, the model will use this mask as a reference to create masked video using salient mask tracking. Will be ignored if mask_video_url is provided prompt: type: string description: >- The text description of the scene, subject, or action to generate in the video. negative_prompt: type: string default: >- letterboxing, borders, black bars, bright colors, overexposed, static, blurred details, subtitles, style, artwork, painting, picture, still, overall gray, worst quality, low quality, JPEG compression residue, ugly, incomplete, extra fingers, poorly drawn hands, poorly drawn faces, deformed, disfigured, malformed limbs, fused fingers, still picture, cluttered background, three legs, many people in the background, walking backwards description: The description of elements to avoid in the generated video. match_input_num_frames: type: boolean num_frames: type: integer minimum: 81 maximum: 241 default: 81 description: Number of frames to generate. match_input_frames_per_second: type: boolean description: Whether to match the input video's frames per second (FPS). frames_per_second: type: integer minimum: 5 maximum: 30 default: 16 description: Frames per second of the generated video. seed: type: integer description: >- Varying the seed integer is a way to get different results for the same other request parameters. Using the same value for an identical request will produce similar results. If unspecified, a random number is chosen. resolution: type: string enum: *ref_53 default: auto description: >- An enumeration where the short side of the video frame determines the resolution. aspect_ratio: type: string enum: *ref_54 default: auto description: The aspect ratio of the generated video. num_inference_steps: type: integer default: 30 description: >- Number of inference steps for sampling. Higher values give better quality but take longer. guidance_scale: type: number default: 5 description: >- Classifier-free guidance scale. Controls prompt adherence / creativity. shift: type: number default: 5 description: Noise schedule shift parameter. Affects temporal dynamics. image_list: type: array items: type: string format: uri description: Array of image URLs for multi-image-to-video generation. image_url: type: string format: uri description: URL of the image to be used as the first frame of the video. last_image_url: type: string format: uri description: >- A direct link to an online image or a Base64-encoded local image to be used as the last frame of the video. enable_safety_checker: type: boolean description: If set to true, the safety checker will be enabled. enable_prompt_expansion: type: boolean description: Whether to enable prompt expansion. preprocess: type: boolean description: Whether to preprocess the input video. acceleration: type: string enum: *ref_55 default: regular description: Acceleration to use for inference. video_quality: type: string enum: *ref_56 default: high description: The quality of the generated video. video_write_mode: type: string enum: *ref_57 default: balanced description: The method used to write the video. num_interpolated_frames: type: integer description: Number of frames to interpolate between the original frames. temporal_downsample_factor: type: integer description: Temporal downsample factor for the video. enable_auto_downsample: type: boolean description: The minimum frames per second to downsample the video to. auto_downsample_min_fps: type: number default: 15 description: The minimum frames per second to downsample the video to. interpolator_model: type: string enum: *ref_58 default: film description: The model to use for interpolation. Rife, or film are available. sync_mode: type: boolean description: >- The synchronization mode for audio and video. Loose or tight are available. required: - model - video_url - prompt Alibaba.v2.wan22VaceOutpainting: type: object properties: model: type: string enum: - alibaba/wan2.2-vace-fun-a14b-outpainting video_url: type: string format: uri description: URL to the source video file. Required for outpainting expand_left: type: boolean default: true description: Whether to expand the video to the left expand_right: type: boolean default: true description: Whether to expand the video to the right expand_top: type: boolean default: true description: Whether to expand the video to the top expand_bottom: type: boolean default: true description: Whether to expand the video to the bottom expand_ratio: type: number default: 0.25 description: >- Amount of expansion. This is a float value between 0 and 1, where 0.25 adds 25% to the original video size on the specified sides prompt: type: string description: >- The text description of the scene, subject, or action to generate in the video. negative_prompt: type: string default: >- letterboxing, borders, black bars, bright colors, overexposed, static, blurred details, subtitles, style, artwork, painting, picture, still, overall gray, worst quality, low quality, JPEG compression residue, ugly, incomplete, extra fingers, poorly drawn hands, poorly drawn faces, deformed, disfigured, malformed limbs, fused fingers, still picture, cluttered background, three legs, many people in the background, walking backwards description: The description of elements to avoid in the generated video. match_input_num_frames: type: boolean num_frames: type: integer minimum: 81 maximum: 241 default: 81 description: Number of frames to generate. match_input_frames_per_second: type: boolean description: Whether to match the input video's frames per second (FPS). frames_per_second: type: integer minimum: 5 maximum: 30 default: 16 description: Frames per second of the generated video. seed: type: integer description: >- Varying the seed integer is a way to get different results for the same other request parameters. Using the same value for an identical request will produce similar results. If unspecified, a random number is chosen. resolution: type: string enum: *ref_53 default: auto description: >- An enumeration where the short side of the video frame determines the resolution. aspect_ratio: type: string enum: *ref_54 default: auto description: The aspect ratio of the generated video. num_inference_steps: type: integer default: 30 description: >- Number of inference steps for sampling. Higher values give better quality but take longer. guidance_scale: type: number default: 5 description: >- Classifier-free guidance scale. Controls prompt adherence / creativity. shift: type: number default: 5 description: Noise schedule shift parameter. Affects temporal dynamics. image_list: type: array items: type: string format: uri description: Array of image URLs for multi-image-to-video generation. image_url: type: string format: uri description: URL of the image to be used as the first frame of the video. last_image_url: type: string format: uri description: >- A direct link to an online image or a Base64-encoded local image to be used as the last frame of the video. enable_safety_checker: type: boolean description: If set to true, the safety checker will be enabled. enable_prompt_expansion: type: boolean description: Whether to enable prompt expansion. preprocess: type: boolean description: Whether to preprocess the input video. acceleration: type: string enum: *ref_55 default: regular description: Acceleration to use for inference. video_quality: type: string enum: *ref_56 default: high description: The quality of the generated video. video_write_mode: type: string enum: *ref_57 default: balanced description: The method used to write the video. num_interpolated_frames: type: integer description: Number of frames to interpolate between the original frames. temporal_downsample_factor: type: integer description: Temporal downsample factor for the video. enable_auto_downsample: type: boolean description: The minimum frames per second to downsample the video to. auto_downsample_min_fps: type: number default: 15 description: The minimum frames per second to downsample the video to. interpolator_model: type: string enum: *ref_58 default: film description: The model to use for interpolation. Rife, or film are available. sync_mode: type: boolean description: >- The synchronization mode for audio and video. Loose or tight are available. required: - model - video_url - prompt Alibaba.v2.wan22VaceReframe: type: object properties: model: type: string enum: - alibaba/wan2.2-vace-fun-a14b-reframe video_url: type: string format: uri description: >- URL to the source video file. This video will be used as a reference for the reframe task zoom_factor: type: number description: >- Zoom factor for the video. When this value is greater than 0, the video will be zoomed in by this factor (in relation to the canvas size,) cutting off the edges of the video. A value of 0 means no zoom trim_borders: type: boolean default: true description: Whether to trim borders from the video prompt: type: string description: The text prompt to guide video generation. Optional for reframing negative_prompt: type: string default: >- letterboxing, borders, black bars, bright colors, overexposed, static, blurred details, subtitles, style, artwork, painting, picture, still, overall gray, worst quality, low quality, JPEG compression residue, ugly, incomplete, extra fingers, poorly drawn hands, poorly drawn faces, deformed, disfigured, malformed limbs, fused fingers, still picture, cluttered background, three legs, many people in the background, walking backwards description: The description of elements to avoid in the generated video. match_input_num_frames: type: boolean default: true num_frames: type: integer minimum: 81 maximum: 241 default: 81 description: Number of frames to generate. match_input_frames_per_second: type: boolean default: true frames_per_second: type: integer minimum: 5 maximum: 30 default: 16 description: Frames per second of the generated video. seed: type: integer description: >- Varying the seed integer is a way to get different results for the same other request parameters. Using the same value for an identical request will produce similar results. If unspecified, a random number is chosen. resolution: type: string enum: *ref_53 default: auto description: >- An enumeration where the short side of the video frame determines the resolution. aspect_ratio: type: string enum: *ref_54 default: auto description: The aspect ratio of the generated video. num_inference_steps: type: integer default: 30 description: >- Number of inference steps for sampling. Higher values give better quality but take longer. guidance_scale: type: number default: 5 description: >- Classifier-free guidance scale. Controls prompt adherence / creativity. shift: type: number default: 5 description: Noise schedule shift parameter. Affects temporal dynamics. image_list: type: array items: type: string format: uri description: Array of image URLs for multi-image-to-video generation. image_url: type: string format: uri description: URL of the image to be used as the first frame of the video. last_image_url: type: string format: uri description: >- A direct link to an online image or a Base64-encoded local image to be used as the last frame of the video. enable_safety_checker: type: boolean description: If set to true, the safety checker will be enabled. enable_prompt_expansion: type: boolean description: Whether to enable prompt expansion. preprocess: type: boolean description: Whether to preprocess the input video. acceleration: type: string enum: *ref_55 default: regular description: Acceleration to use for inference. video_quality: type: string enum: *ref_56 default: high description: The quality of the generated video. video_write_mode: type: string enum: *ref_57 default: balanced description: The method used to write the video. num_interpolated_frames: type: integer description: Number of frames to interpolate between the original frames. temporal_downsample_factor: type: integer description: Temporal downsample factor for the video. enable_auto_downsample: type: boolean description: The minimum frames per second to downsample the video to. auto_downsample_min_fps: type: number default: 15 description: The minimum frames per second to downsample the video to. interpolator_model: type: string enum: *ref_58 default: film description: The model to use for interpolation. Rife, or film are available. sync_mode: type: boolean description: >- The synchronization mode for audio and video. Loose or tight are available. required: - model - video_url Alibaba.v2.wan22AnimateMove: type: object properties: model: type: string enum: - alibaba/wan2.2-14b-animate-move video_url: type: string format: uri description: URL of the input video image_url: type: string format: uri description: >- URL of the input image. If the input image does not match the chosen aspect ratio, it is resized and center cropped resolution: type: string enum: &ref_59 - 480p - 580p - 720p default: 480p description: Resolution of the generated video (480p, 580p, or 720p) seed: type: integer description: >- Varying the seed integer is a way to get different results for the same other request parameters. Using the same value for an identical request will produce similar results. If unspecified, a random number is chosen. num_inference_steps: type: integer default: 20 description: >- Number of inference steps for sampling. Higher values give better quality but take longer enable_safety_checker: type: boolean description: >- If set to true, input data will be checked for safety before processing shift: type: number default: 5 description: Shift value for the video. Must be between 1.0 and 10.0 video_quality: type: string enum: &ref_60 - low - medium - high - maximum default: high description: >- The quality of the output video. Higher quality means better visual quality but larger file size video_write_mode: type: string enum: &ref_61 - fast - balanced - small default: balanced description: >- The write mode of the output video. Faster write mode means faster results but larger file size, balanced write mode is a good compromise between speed and quality, and small write mode is the slowest but produces the smallest file size required: - model - video_url - image_url Alibaba.v2.wan22AnimateReplace: type: object properties: model: type: string enum: - alibaba/wan2.2-14b-animate-replace video_url: type: string format: uri description: URL of the input video image_url: type: string format: uri description: >- URL of the input image. If the input image does not match the chosen aspect ratio, it is resized and center cropped resolution: type: string enum: *ref_59 default: 480p description: Resolution of the generated video (480p, 580p, or 720p) seed: type: integer description: >- Varying the seed integer is a way to get different results for the same other request parameters. Using the same value for an identical request will produce similar results. If unspecified, a random number is chosen. num_inference_steps: type: integer default: 20 description: >- Number of inference steps for sampling. Higher values give better quality but take longer enable_safety_checker: type: boolean description: >- If set to true, input data will be checked for safety before processing shift: type: number default: 5 description: Shift value for the video. Must be between 1.0 and 10.0 video_quality: type: string enum: *ref_60 default: high description: >- The quality of the output video. Higher quality means better visual quality but larger file size video_write_mode: type: string enum: *ref_61 default: balanced description: >- The write mode of the output video. Faster write mode means faster results but larger file size, balanced write mode is a good compromise between speed and quality, and small write mode is the slowest but produces the smallest file size required: - model - video_url - image_url Video.v2.kandinsky5TextToVideo: type: object properties: model: type: string enum: - sber-ai/kandinsky5-t2v prompt: type: string description: >- The text description of the scene, subject, or action to generate in the video. aspect_ratio: type: string enum: - '16:9' - '9:16' - '1:1' default: '16:9' description: The aspect ratio of the generated video. duration: type: integer description: The length of the output video in seconds. enum: - 5 - 10 num_inference_steps: type: integer default: 30 description: >- Number of inference steps for sampling. Higher values give better quality but take longer. required: - model - prompt Video.v2.kandinsky5TextToVideoDistill: type: object properties: model: type: string enum: - sber-ai/kandinsky5-distill-t2v prompt: type: string description: >- The text description of the scene, subject, or action to generate in the video. aspect_ratio: type: string enum: - '16:9' - '9:16' - '1:1' default: '16:9' description: The aspect ratio of the generated video. duration: type: integer description: The length of the output video in seconds. enum: - 5 - 10 required: - model - prompt Video.v2.longcatDistilled: type: object properties: model: type: string enum: - longcat/distilled/480p - longcat/distilled/720p prompt: type: string description: >- The text description of the scene, subject, or action to generate in the video. image_url: type: string format: uri description: >- A direct link to an online image or a Base64-encoded local image that will serve as the visual base or the first frame for the video. fps: type: integer minimum: 1 maximum: 60 default: 15 description: Frames per second of the generated video. num_frames: type: integer minimum: 17 maximum: 961 default: 162 description: Number of frames to generate. aspect_ratio: type: string enum: - '16:9' - '9:16' - '1:1' default: '16:9' description: >- The aspect ratio of the generated video. This parameter is ignored if image_url is provided. num_inference_steps: type: integer minimum: 2 maximum: 16 default: 12 description: >- Number of inference steps for sampling. Higher values give better quality but take longer. seed: type: integer description: >- Varying the seed integer is a way to get different results for the same other request parameters. Using the same value for an identical request will produce similar results. If unspecified, a random number is chosen. enable_prompt_expansion: type: boolean default: false description: Whether to enable prompt expansion. enable_safety_checker: type: boolean default: true description: If set to true, the safety checker will be enabled. video_output_type: type: string enum: - X264 (.mp4) - VP9 (.webm) - PRORES4444 (.mov) - GIF (.gif) default: X264 (.mp4) description: The output type of the generated video. video_quality: type: string enum: - low - medium - high - maximum default: high description: The quality of the generated video. video_write_mode: type: string enum: - fast - balanced - small default: balanced description: The method used to write the video. required: - model - prompt Video.v2.PollVideoResponseDTO: type: object properties: id: type: string description: The ID of the generated video. example: 60ac7c34-3224-4b14-8e7d-0aa0db708325 status: type: string enum: - queued - generating - completed - error description: The current status of the generation task. example: completed video: type: object nullable: true properties: url: type: string format: uri description: The URL where the file can be downloaded from. example: >- https://cdn.aimlapi.com/generations/hedgehog/1759866285599-0cdfb138-c03a-49d4-a601-4f6413e27b15.mp4 duration: type: number nullable: true description: The duration of the video. example: 8 required: - url duration: type: number nullable: true description: The duration of the video. example: 8 error: nullable: true description: Description of the error, if any. meta: type: object nullable: true properties: usage: type: object nullable: true properties: credits_used: type: number description: The number of tokens consumed during generation. example: 120000 required: - credits_used description: Additional details about the generation. required: - id - status Audio.v2.SubmitGenerationPayloadDTO: oneOf: - type: object properties: model: type: string enum: - elevenlabs/eleven_music prompt: type: string maxLength: 2000 description: >- A text description that can define the genre, mood, instruments, vocals, tempo, structure, and even lyrics of the track. It can be high-level (“peaceful meditation with voiceover”) or detailed (“solo piano in C minor, 90 BPM, raw and emotional”). Use keywords to control genre, emotional tone, vocals (e.g., a cappella, two singers harmonizing), structure (e.g., “lyrics begin at 15 seconds”), or provide custom lyrics directly in the prompt. music_length_ms: type: integer minimum: 10000 maximum: 300000 default: 10000 description: >- The length of the song to generate in milliseconds. This parameter may not always be respected by the model, and the actual audio length can differ. format: milliseconds required: - model - prompt - type: object properties: model: type: string enum: - stable-audio prompt: type: string description: The prompt to generate audio. seconds_start: type: integer maximum: 47 minimum: 1 description: The start point of the audio clip to generate. seconds_total: type: integer maximum: 47 minimum: 1 default: 30 description: The duration of the audio clip to generate. steps: type: integer minimum: 1 maximum: 1000 default: 100 description: The number of steps to denoise the audio. required: - model - prompt - type: object properties: model: type: string enum: - minimax-music prompt: type: string description: >- Lyrics with optional formatting. You can use a newline to separate each line of lyrics. You can use two newlines to add a pause between lines. You can use double hash marks (##) at the beginning and end of the lyrics to add accompaniment. Maximum 600 characters. reference_audio_url: type: string format: uri description: >- Reference song, should contain music and vocals. Must be a .wav or .mp3 file longer than 15 seconds. required: - model - prompt - reference_audio_url - type: object properties: model: type: string enum: - google/lyria2 prompt: type: string description: The prompt to generate audio. negative_prompt: type: string description: A description of what to exclude from the generated audio seed: type: integer minimum: 0 description: >- A seed for deterministic generation. If provided, the model will attempt to produce the same audio given the same prompt and other parameters. required: - model - prompt - type: object properties: model: type: string enum: - minimax/music-1.5 prompt: type: string minLength: 10 maxLength: 300 description: >- A description of the music, specifying style, mood, and scenario. Length: 10–300 characters. lyrics: type: string minLength: 10 maxLength: 3000 description: >- Lyrics of the song. Use ( ) to separate lines. You may add structure tags like [Intro], [Verse], [Chorus], [Bridge], [Outro] to enhance the arrangement. Length: 10–3000 characters. example: |- [Verse] Streetlights flicker, the night breeze sighs Shadows stretch as I walk alone An old coat wraps my silent sorrow Wandering, longing, where should I go [Chorus] Pushing the wooden door, the aroma spreads In a familiar corner, a stranger gazes audio_setting: type: object properties: sample_rate: type: integer description: The sampling rate of the generated music. enum: &ref_62 - 16000 - 24000 - 32000 - 44100 bitrate: type: integer description: The bit rate of the generated music. enum: &ref_63 - 32000 - 64000 - 128000 - 256000 format: type: string enum: &ref_64 - mp3 - wav - pcm description: The format of the generated music. required: - format required: - model - prompt - lyrics - type: object properties: model: type: string enum: - minimax/music-2.0 prompt: type: string minLength: 10 maxLength: 2000 description: >- A description of the music, specifying style, mood, and scenario. Length: 10–2000 characters. lyrics: type: string minLength: 10 maxLength: 3000 description: >- Lyrics of the song. Use ( ) to separate lines. You may add structure tags like [Intro], [Verse], [Chorus], [Bridge], [Outro] to enhance the arrangement. Length: 10–3000 characters. example: |- [Verse] Streetlights flicker, the night breeze sighs Shadows stretch as I walk alone An old coat wraps my silent sorrow Wandering, longing, where should I go [Chorus] Pushing the wooden door, the aroma spreads In a familiar corner, a stranger gazes audio_setting: type: object properties: sample_rate: type: integer description: The sampling rate of the generated music. enum: *ref_62 bitrate: type: integer description: The bit rate of the generated music. enum: *ref_63 format: type: string enum: *ref_64 description: The format of the generated music. required: - format required: - model - prompt - lyrics Voice.v1.SpeechToTextPayloadDTO: anyOf: - type: object properties: model: type: string enum: - '#g1_nova-2-general' - '#g1_nova-2-meeting' - '#g1_nova-2-phonecall' - '#g1_nova-2-voicemail' - '#g1_nova-2-finance' - '#g1_nova-2-conversationalai' - '#g1_nova-2-video' - '#g1_nova-2-medical' - '#g1_nova-2-drivethru' - '#g1_nova-2-automotive' - '#g1_whisper-large' - '#g1_whisper-medium' - '#g1_whisper-small' - '#g1_whisper-tiny' - '#g1_whisper-base' custom_intent: anyOf: - type: string - type: array items: type: string description: >- A custom intent you want the model to detect within your input audio if present. Submit up to 100. custom_topic: anyOf: - type: string - type: array items: type: string description: >- A custom topic you want the model to detect within your input audio if present. Submit up to 100. custom_intent_mode: type: string enum: &ref_65 - strict - extended description: >- Sets how the model will interpret strings submitted to the custom_intent param. When strict, the model will only return intents submitted using the custom_intent param. When extended, the model will return its own detected intents in addition those submitted using the custom_intents param. custom_topic_mode: type: string enum: &ref_66 - strict - extended description: >- Sets how the model will interpret strings submitted to the custom_topic param. When strict, the model will only return topics submitted using the custom_topic param. When extended, the model will return its own detected topics in addition to those submitted using the custom_topic param. detect_language: type: boolean description: >- Enables language detection to identify the dominant language spoken in the submitted audio. detect_entities: type: boolean description: >- When Entity Detection is enabled, the Punctuation feature will be enabled by default. detect_topics: type: boolean description: >- Detects the most important and relevant topics that are referenced in speech within the audio. diarize: type: boolean description: >- Recognizes speaker changes. Each word in the transcript will be assigned a speaker number starting at 0. dictation: type: boolean description: >- Identifies and extracts key entities from content in submitted audio. diarize_version: type: string description: '' extra: type: string description: >- Arbitrary key-value pairs that are attached to the API response for usage in downstream processing. filler_words: type: boolean description: >- Filler Words can help transcribe interruptions in your audio, like “uh” and “um”. intents: type: boolean description: Recognizes speaker intent throughout a transcript or text. keywords: type: string description: >- Keywords can boost or suppress specialized terminology and brands. language: type: string description: >- The BCP-47 language tag that hints at the primary spoken language. Depending on the Model and API endpoint you choose only certain languages are available measurements: type: boolean description: >- Spoken measurements will be converted to their corresponding abbreviations multi_channel: type: boolean description: Transcribes each audio channel independently numerals: type: boolean description: >- Numerals converts numbers from written format to numerical format paragraphs: type: boolean description: Splits audio into paragraphs to improve transcript readability profanity_filter: type: boolean description: >- Profanity Filter looks for recognized profanity and converts it to the nearest recognized non-profane word or removes it from the transcript completely punctuate: type: boolean description: Adds punctuation and capitalization to the transcript search: type: string description: Search for terms or phrases in submitted audio sentiment: type: boolean description: Recognizes the sentiment throughout a transcript or text smart_format: type: boolean description: >- Applies formatting to transcript output. When set to true, additional formatting will be applied to transcripts to improve readability summarize: type: string description: >- Summarizes content. For Listen API, supports string version option. For Read API, accepts boolean only. tag: type: array items: type: string description: >- Labels your requests for the purpose of identification during usage reporting topics: type: boolean description: Detects topics throughout a transcript or text utterances: type: boolean description: Segments speech into meaningful semantic units utt_split: type: number description: >- Seconds to wait before detecting a pause between words in submitted audio url: type: string format: uri required: - model - url - type: object properties: model: type: string enum: - '#g1_nova-2-general' - '#g1_nova-2-meeting' - '#g1_nova-2-phonecall' - '#g1_nova-2-voicemail' - '#g1_nova-2-finance' - '#g1_nova-2-conversationalai' - '#g1_nova-2-video' - '#g1_nova-2-medical' - '#g1_nova-2-drivethru' - '#g1_nova-2-automotive' - '#g1_whisper-large' - '#g1_whisper-medium' - '#g1_whisper-small' - '#g1_whisper-tiny' - '#g1_whisper-base' custom_intent: anyOf: - type: string - type: array items: type: string description: >- A custom intent you want the model to detect within your input audio if present. Submit up to 100. custom_topic: anyOf: - type: string - type: array items: type: string description: >- A custom topic you want the model to detect within your input audio if present. Submit up to 100. custom_intent_mode: type: string enum: *ref_65 description: >- Sets how the model will interpret strings submitted to the custom_intent param. When strict, the model will only return intents submitted using the custom_intent param. When extended, the model will return its own detected intents in addition those submitted using the custom_intents param. custom_topic_mode: type: string enum: *ref_66 description: >- Sets how the model will interpret strings submitted to the custom_topic param. When strict, the model will only return topics submitted using the custom_topic param. When extended, the model will return its own detected topics in addition to those submitted using the custom_topic param. detect_language: type: boolean description: >- Enables language detection to identify the dominant language spoken in the submitted audio. detect_entities: type: boolean description: >- When Entity Detection is enabled, the Punctuation feature will be enabled by default. detect_topics: type: boolean description: >- Detects the most important and relevant topics that are referenced in speech within the audio. diarize: type: boolean description: >- Recognizes speaker changes. Each word in the transcript will be assigned a speaker number starting at 0. dictation: type: boolean description: >- Identifies and extracts key entities from content in submitted audio. diarize_version: type: string description: '' extra: type: string description: >- Arbitrary key-value pairs that are attached to the API response for usage in downstream processing. filler_words: type: boolean description: >- Filler Words can help transcribe interruptions in your audio, like “uh” and “um”. intents: type: boolean description: Recognizes speaker intent throughout a transcript or text. keywords: type: string description: >- Keywords can boost or suppress specialized terminology and brands. language: type: string description: >- The BCP-47 language tag that hints at the primary spoken language. Depending on the Model and API endpoint you choose only certain languages are available measurements: type: boolean description: >- Spoken measurements will be converted to their corresponding abbreviations multi_channel: type: boolean description: Transcribes each audio channel independently numerals: type: boolean description: >- Numerals converts numbers from written format to numerical format paragraphs: type: boolean description: Splits audio into paragraphs to improve transcript readability profanity_filter: type: boolean description: >- Profanity Filter looks for recognized profanity and converts it to the nearest recognized non-profane word or removes it from the transcript completely punctuate: type: boolean description: Adds punctuation and capitalization to the transcript search: type: string description: Search for terms or phrases in submitted audio sentiment: type: boolean description: Recognizes the sentiment throughout a transcript or text smart_format: type: boolean description: >- Applies formatting to transcript output. When set to true, additional formatting will be applied to transcripts to improve readability summarize: type: string description: >- Summarizes content. For Listen API, supports string version option. For Read API, accepts boolean only. tag: type: array items: type: string description: >- Labels your requests for the purpose of identification during usage reporting topics: type: boolean description: Detects topics throughout a transcript or text utterances: type: boolean description: Segments speech into meaningful semantic units utt_split: type: number description: >- Seconds to wait before detecting a pause between words in submitted audio required: - model - type: object properties: model: type: string enum: - aai/slam-1 - aai/universal audio: type: object properties: buffer: nullable: true mimetype: type: string size: type: integer originalname: type: string encoding: type: string fieldname: type: string required: - mimetype - originalname - encoding - fieldname description: The audio file to transcribe. audio_start_from: type: integer description: >- The point in time, in milliseconds, in the file at which the transcription was started. audio_end_at: type: integer description: >- The point in time, in milliseconds, in the file at which the transcription was terminated. language_code: type: string description: >- The language of your audio file. Possible values are found in Supported Languages. The default value is 'en_us'. language_confidence_threshold: type: number minimum: 0 maximum: 1 description: >- The confidence threshold for the automatically detected language. An error will be returned if the language confidence is below this threshold. Defaults to 0. language_detection: type: boolean description: >- Enable Automatic language detection, either true or false. Available for universal model only. punctuate: type: boolean nullable: true default: null description: Adds punctuation and capitalization to the transcript format_text: type: boolean default: true description: Enable Text Formatting, can be true or false. disfluencies: type: boolean default: false description: >- Transcribe Filler Words, like "umm", in your media file; can be true or false. multichannel: type: boolean default: false description: Enable Multichannel transcription, can be true or false. speaker_labels: type: boolean nullable: true default: null description: Enable Speaker diarization, can be true or false. speakers_expected: type: integer nullable: true default: null description: >- Tell the speaker label model how many speakers it should attempt to identify. See Speaker diarization for more details. content_safety: type: boolean default: false description: Enable Content Moderation, can be true or false. iab_categories: type: boolean default: false description: Enable Topic Detection, can be true or false. custom_spelling: type: array items: type: object properties: from: type: string to: type: string required: - from - to description: >- Customize how words are spelled and formatted using to and from values. auto_highlights: type: boolean default: false description: Enable Key Phrases, either true or false. word_boost: type: array items: type: string description: >- The list of custom vocabulary to boost transcription probability for. boost_param: type: string enum: - low - default - high description: >- How much to boost specified words. Allowed values: low, default, high. filter_profanity: type: boolean default: false description: >- Filter profanity from the transcribed text, can be true or false. redact_pii: type: boolean default: false description: >- Redact PII from the transcribed text using the Redact PII model, can be true or false. redact_pii_audio: type: boolean default: false description: >- Generate a copy of the original media file with spoken PII "beeped" out, can be true or false. See PII redaction for more details. redact_pii_audio_quality: type: string enum: - mp3 - wav description: >- Controls the filetype of the audio created by redact_pii_audio. Currently supports mp3 (default) and wav. See PII redaction for more details. redact_pii_policies: type: array items: type: string enum: - account_number - banking_information - blood_type - credit_card_cvv - credit_card_expiration - credit_card_number - date - date_interval - date_of_birth - drivers_license - drug - duration - email_address - event - filename - gender_sexuality - healthcare_number - injury - ip_address - language - location - marital_status - medical_condition - medical_process - money_amount - nationality - number_sequence - occupation - organization - passport_number - password - person_age - person_name - phone_number - physical_attribute - political_affiliation - religion - statistics - time - url - us_social_security_number - username - vehicle_id - zodiac_sign description: >- The list of PII Redaction policies to enable. See PII redaction for more details. redact_pii_sub: type: string enum: - entity_name - hash description: >- The replacement logic for detected PII, can be `entity_type` or `hash`. See PII redaction for more details. sentiment_analysis: type: boolean default: false description: Enable Sentiment Analysis, can be true or false. entity_detection: type: boolean default: false description: Enable Entity Detection, can be true or false. summarization: type: boolean default: false description: Enable Summarization, can be true or false. summary_model: type: string enum: - informative - conversational - catchy description: >- The model to summarize the transcript. Allowed values: informative, conversational, catchy. summary_type: type: string enum: - bullets - bullets_verbose - gist - headline - paragraph description: >- The type of summary. Allowed values: bullets, bullets_verbose, gist, headline, paragraph. auto_chapters: type: boolean default: false description: Enable Auto Chapters, either true or false. speech_threshold: type: number minimum: 0 maximum: 1 description: >- Reject audio files that contain less than this fraction of speech. Valid values are in the range [0, 1] inclusive. required: - model - audio - type: object properties: model: type: string enum: - aai/slam-1 - aai/universal url: type: string format: uri description: URL of the input audio file. audio_start_from: type: integer description: >- The point in time, in milliseconds, in the file at which the transcription was started. audio_end_at: type: integer description: >- The point in time, in milliseconds, in the file at which the transcription was terminated. language_code: type: string description: >- The language of your audio file. Possible values are found in Supported Languages. The default value is 'en_us'. language_confidence_threshold: type: number minimum: 0 maximum: 1 description: >- The confidence threshold for the automatically detected language. An error will be returned if the language confidence is below this threshold. Defaults to 0. language_detection: type: boolean description: >- Enable Automatic language detection, either true or false. Available for universal model only. punctuate: type: boolean nullable: true default: null description: Adds punctuation and capitalization to the transcript format_text: type: boolean default: true description: Enable Text Formatting, can be true or false. disfluencies: type: boolean default: false description: >- Transcribe Filler Words, like "umm", in your media file; can be true or false. multichannel: type: boolean default: false description: Enable Multichannel transcription, can be true or false. speaker_labels: type: boolean nullable: true default: false description: Enable Speaker diarization, can be true or false. speakers_expected: type: integer nullable: true default: null description: >- Tell the speaker label model how many speakers it should attempt to identify. See Speaker diarization for more details. content_safety: type: boolean default: false description: Enable Content Moderation, can be true or false. iab_categories: type: boolean default: false description: Enable Topic Detection, can be true or false. custom_spelling: type: array items: type: object properties: from: type: string to: type: string required: - from - to description: >- Customize how words are spelled and formatted using to and from values. auto_highlights: type: boolean default: false description: Enable Key Phrases, either true or false. word_boost: type: array items: type: string description: >- The list of custom vocabulary to boost transcription probability for. boost_param: type: string enum: - low - default - high description: >- How much to boost specified words. Allowed values: low, default, high. filter_profanity: type: boolean default: false description: >- Filter profanity from the transcribed text, can be true or false. redact_pii: type: boolean default: false description: >- Redact PII from the transcribed text using the Redact PII model, can be true or false. redact_pii_audio: type: boolean default: false description: >- Generate a copy of the original media file with spoken PII "beeped" out, can be true or false. See PII redaction for more details. redact_pii_audio_quality: type: string enum: - mp3 - wav description: >- Controls the filetype of the audio created by redact_pii_audio. Currently supports mp3 (default) and wav. See PII redaction for more details. redact_pii_policies: type: array items: type: string enum: - account_number - banking_information - blood_type - credit_card_cvv - credit_card_expiration - credit_card_number - date - date_interval - date_of_birth - drivers_license - drug - duration - email_address - event - filename - gender_sexuality - healthcare_number - injury - ip_address - language - location - marital_status - medical_condition - medical_process - money_amount - nationality - number_sequence - occupation - organization - passport_number - password - person_age - person_name - phone_number - physical_attribute - political_affiliation - religion - statistics - time - url - us_social_security_number - username - vehicle_id - zodiac_sign description: >- The list of PII Redaction policies to enable. See PII redaction for more details. redact_pii_sub: type: string enum: - entity_name - hash description: >- The replacement logic for detected PII, can be `entity_type` or `hash`. See PII redaction for more details. sentiment_analysis: type: boolean default: false description: Enable Sentiment Analysis, can be true or false. entity_detection: type: boolean default: false description: Enable Entity Detection, can be true or false. summarization: type: boolean default: false description: Enable Summarization, can be true or false. summary_model: type: string enum: - informative - conversational - catchy description: >- The model to summarize the transcript. Allowed values: informative, conversational, catchy. summary_type: type: string enum: - bullets - bullets_verbose - gist - headline - paragraph description: >- The type of summary. Allowed values: bullets, bullets_verbose, gist, headline, paragraph. auto_chapters: type: boolean default: false description: Enable Auto Chapters, either true or false. speech_threshold: type: number minimum: 0 maximum: 1 description: >- Reject audio files that contain less than this fraction of speech. Valid values are in the range [0, 1] inclusive. required: - model - url - type: object properties: model: type: string enum: - openai/gpt-4o-transcribe - openai/gpt-4o-mini-transcribe language: type: string description: >- The BCP-47 language tag that hints at the primary spoken language. Depending on the Model and API endpoint you choose only certain languages are available prompt: type: string description: >- An optional text to guide the model's style or continue a previous audio segment. The prompt should match the audio language. temperature: type: number minimum: 0 maximum: 1 default: 0 description: >- The sampling temperature, between 0 and 1. Higher values like 0.8 will make the output more random, while lower values like 0.2 will make it more focused and deterministic. url: type: string format: uri description: URL of the input audio file. required: - model - url - type: object properties: model: type: string enum: - openai/gpt-4o-transcribe - openai/gpt-4o-mini-transcribe language: type: string description: >- The BCP-47 language tag that hints at the primary spoken language. Depending on the Model and API endpoint you choose only certain languages are available prompt: type: string description: >- An optional text to guide the model's style or continue a previous audio segment. The prompt should match the audio language. temperature: type: number minimum: 0 maximum: 1 default: 0 description: >- The sampling temperature, between 0 and 1. Higher values like 0.8 will make the output more random, while lower values like 0.2 will make it more focused and deterministic. required: - model Voice.v1.TextToSpeechPayload: anyOf: - type: object properties: model: type: string enum: - '#g1_aura-asteria-en' - '#g1_aura-hera-en' - '#g1_aura-luna-en' - '#g1_aura-stella-en' - '#g1_aura-athena-en' - '#g1_aura-zeus-en' - '#g1_aura-orion-en' - '#g1_aura-arcas-en' - '#g1_aura-perseus-en' - '#g1_aura-angus-en' - '#g1_aura-orpheus-en' - '#g1_aura-helios-en' - '#g1_aura-2-amalthea-en' - '#g1_aura-2-andromeda-en' - '#g1_aura-2-apollo-en' - '#g1_aura-2-arcas-en' - '#g1_aura-2-aries-en' - '#g1_aura-2-asteria-en' - '#g1_aura-2-athena-en' - '#g1_aura-2-atlas-en' - '#g1_aura-2-aurora-en' - '#g1_aura-2-callista-en' - '#g1_aura-2-cora-en' - '#g1_aura-2-cordelia-en' - '#g1_aura-2-delia-en' - '#g1_aura-2-draco-en' - '#g1_aura-2-electra-en' - '#g1_aura-2-harmonia-en' - '#g1_aura-2-helena-en' - '#g1_aura-2-hera-en' - '#g1_aura-2-hermes-en' - '#g1_aura-2-hyperion-en' - '#g1_aura-2-iris-en' - '#g1_aura-2-janus-en' - '#g1_aura-2-juno-en' - '#g1_aura-2-jupiter-en' - '#g1_aura-2-luna-en' - '#g1_aura-2-mars-en' - '#g1_aura-2-minerva-en' - '#g1_aura-2-neptune-en' - '#g1_aura-2-odysseus-en' - '#g1_aura-2-ophelia-en' - '#g1_aura-2-orion-en' - '#g1_aura-2-orpheus-en' - '#g1_aura-2-pandora-en' - '#g1_aura-2-phoebe-en' - '#g1_aura-2-pluto-en' - '#g1_aura-2-saturn-en' - '#g1_aura-2-selene-en' - '#g1_aura-2-thalia-en' - '#g1_aura-2-theia-en' - '#g1_aura-2-vesta-en' - '#g1_aura-2-zeus-en' - '#g1_aura-2-celeste-es' - '#g1_aura-2-estrella-es' - '#g1_aura-2-nestor-es' text: type: string description: The text content to be converted to speech. container: type: string description: >- The file format wrapper for the output audio. The available options depend on the encoding type. encoding: type: string enum: - linear16 - mulaw - alaw - mp3 - opus - flac - aac default: linear16 description: Specifies the expected encoding of your audio output sample_rate: type: string description: Audio sample rate in Hz. required: - model - text - oneOf: - type: object properties: model: type: string enum: - elevenlabs/eleven_multilingual_v2 - elevenlabs/eleven_turbo_v2_5 text: type: string description: The text content to be converted to speech. voice: type: string enum: &ref_67 - Rachel - Drew - Clyde - Paul - Aria - Domi - Dave - Roger - Fin - Sarah - Antoni - Laura - Thomas - Charlie - George - Emily - Elli - Callum - Patrick - River - Harry - Liam - Dorothy - Josh - Arnold - Charlotte - Alice - Matilda - James - Joseph - Will - Jeremy - Jessica - Eric - Michael - Ethan - Chris - Gigi - Freya - Santa Claus - Brian - Grace - Daniel - Lily - Serena - Adam - Nicole - Bill - Jessie - Sam - Glinda - Giovanni - Mimi default: Rachel description: Name of the voice to be used. apply_text_normalization: type: string enum: &ref_68 - auto - 'on' - 'off' description: >- This parameter controls text normalization with three modes: 'auto', 'on', and 'off'. When set to 'auto', the system will automatically decide whether to apply text normalization (e.g., spelling out numbers). With 'on', text normalization will always be applied, while with 'off', it will be skipped. next_text: type: string description: >- The text that comes after the text of the current request. Can be used to improve the speech's continuity when concatenating together multiple generations or to influence the speech's continuity in the current generation. previous_text: type: string description: >- The text that came before the text of the current request. Can be used to improve the speech's continuity when concatenating together multiple generations or to influence the speech's continuity in the current generation. output_format: type: string enum: &ref_69 - mp3_22050_32 - mp3_44100_32 - mp3_44100_64 - mp3_44100_96 - mp3_44100_128 - mp3_44100_192 - pcm_8000 - pcm_16000 - pcm_22050 - pcm_24000 - pcm_44100 - pcm_48000 - ulaw_8000 - alaw_8000 - opus_48000_32 - opus_48000_64 - opus_48000_96 - opus_48000_128 - opus_48000_192 description: >- Format of the output content for non-streaming requests. Controls how the generated audio data is encoded in the response. voice_settings: type: object properties: stability: type: number description: >- Determines how stable the voice is and the randomness between each generation. Lower values introduce broader emotional range for the voice. Higher values can result in a monotonous voice with limited emotion. use_speaker_boost: type: boolean description: >- This setting boosts the similarity to the original speaker. Using this setting requires a slightly higher computational load, which in turn increases latency. similarity_boost: type: number description: >- Determines how closely the AI should adhere to the original voice when attempting to replicate it. style: type: number description: >- Determines the style exaggeration of the voice. This setting attempts to amplify the style of the original speaker. It does consume additional computational resources and might increase latency if set to anything other than 0. speed: type: number description: >- Adjusts the speed of the voice. A value of 1.0 is the default speed, while values less than 1.0 slow down the speech, and values greater than 1.0 speed it up. description: >- Voice settings overriding stored settings for the given voice. They are applied only on the given request. seed: type: integer description: >- If specified, our system will make a best effort to sample deterministically, such that repeated requests with the same seed and parameters should return the same result. Determinism is not guaranteed. required: - model - text - type: object properties: model: type: string enum: - elevenlabs/v3_alpha text: type: string description: The text content to be converted to speech. voice: type: string enum: *ref_67 default: Rachel description: Name of the voice to be used. apply_text_normalization: type: string enum: *ref_68 description: >- This parameter controls text normalization with three modes: 'auto', 'on', and 'off'. When set to 'auto', the system will automatically decide whether to apply text normalization (e.g., spelling out numbers). With 'on', text normalization will always be applied, while with 'off', it will be skipped. output_format: type: string enum: *ref_69 description: >- Format of the output content for non-streaming requests. Controls how the generated audio data is encoded in the response. voice_settings: type: object properties: stability: type: number description: >- Determines how stable the voice is and the randomness between each generation. Lower values introduce broader emotional range for the voice. Higher values can result in a monotonous voice with limited emotion. use_speaker_boost: type: boolean description: >- This setting boosts the similarity to the original speaker. Using this setting requires a slightly higher computational load, which in turn increases latency. similarity_boost: type: number description: >- Determines how closely the AI should adhere to the original voice when attempting to replicate it. style: type: number description: >- Determines the style exaggeration of the voice. This setting attempts to amplify the style of the original speaker. It does consume additional computational resources and might increase latency if set to anything other than 0. speed: type: number description: >- Adjusts the speed of the voice. A value of 1.0 is the default speed, while values less than 1.0 slow down the speech, and values greater than 1.0 speed it up. description: >- Voice settings overriding stored settings for the given voice. They are applied only on the given request. seed: type: integer description: >- If specified, our system will make a best effort to sample deterministically, such that repeated requests with the same seed and parameters should return the same result. Determinism is not guaranteed. required: - model - text - $ref: '#/components/schemas/Minimax.v2.TextToSpeechPayloadDTO' - type: object properties: model: type: string enum: - microsoft/vibevoice-7b - microsoft/vibevoice-1.5b script: type: string minLength: 1 maxLength: 5000 description: >- The script to convert to speech. Can be formatted with "Speaker X:" prefixes for multi-speaker dialogues. speakers: type: array items: type: object properties: preset: type: string enum: - Alice [EN] - Alice [EN] (Background Music) - Carter [EN] - Frank [EN] - Maya [EN] - Anchen [ZH] (Background Music) - Bowen [ZH] - Xinran [ZH] description: >- Default voice preset to use for the speaker. Not used if audio_url is provided. audio_url: type: string format: uri description: >- URL to a voice sample audio file. If provided, preset will be ignored. minItems: 1 maxItems: 4 default: - preset: Alice [EN] description: >- List of speakers to use for the script. If not provided, will be inferred from the script or voice samples. seed: type: integer description: >- If specified, our system will make a best effort to sample deterministically, such that repeated requests with the same seed and parameters should return the same result. Determinism is not guaranteed. cfg_scale: type: number minimum: 0.1 maximum: 2 default: 1.3 description: >- The CFG (Classifier Free Guidance) scale is a measure of how close you want the model to stick to your prompt. required: - model - script - type: object properties: model: type: string enum: - alibaba/qwen3-tts-flash text: type: string minLength: 1 maxLength: 600 description: The text content to be converted to speech. voice: type: string enum: - Cherry - Ethan - Nofish - Jennifer - Ryan - Katerina - Elias - Jada - Dylan - Sunny - Li - Marcus - Roy - Peter - Rocky - Kiki - Eric default: Cherry description: Name of the voice to be used. required: - model - text - type: object properties: model: type: string enum: - openai/gpt-4o-mini-tts - openai/tts-1 - openai/tts-1-hd text: type: string minLength: 1 maxLength: 4096 description: The text content to be converted to speech. voice: type: string enum: - alloy - ash - ballad - coral - echo - fable - nova - onyx - sage - shimmer - verse default: alloy description: Name of the voice to be used. style: type: string description: >- Determines the style exaggeration of the voice. This setting attempts to amplify the style of the original speaker. It does consume additional computational resources and might increase latency if set to anything other than 0. response_format: type: string enum: - mp3 - opus - aac - flac - wav - pcm default: mp3 description: >- Format of the output content for non-streaming requests. Controls how the generated audio data is encoded in the response. speed: type: number minimum: 0.25 maximum: 4 default: 1 description: >- Adjusts the speed of the voice. A value of 1.0 is the default speed, while values less than 1.0 slow down the speech, and values greater than 1.0 speed it up. required: - model - text - type: object properties: model: type: string enum: - hume/octave-2 text: type: string minLength: 1 maxLength: 500000 description: The text content to be converted to speech. voice: type: string enum: - Vince Douglas - Male English Actor - Ava Song - Campfire Narrator - TikTok Fashion Influencer - Colton Rivers - Literature Professor - Booming American Narrator - Imani Carter - Terrence Bentley - Nature Documentary Narrator - Alice Bennett - Sitcom Girl - Unserious Movie Trailer Narrator - Articulate ASMR British Narrator - Big Dicky - English Children's Book Narrator - Sebastian Lockwood - Donovan Sinclair - Booming British Narrator - Relaxing ASMR Woman - Lady Elizabeth - Male Protagonist - Tough Guy - French Chef - Spanish Instructor - Charming Cowgirl default: Vince Douglas description: Name of the voice to be used. format: type: string enum: - wav - mp3 description: >- Audio output format. MP3 provides good compression and compatibility, PCM offers uncompressed high quality, and FLAC provides lossless compression. required: - model - text - type: object properties: model: type: string enum: - inworld/tts-1 - inworld/tts-1-max - inworld/tts-1-5-max - inworld/tts-1-5-mini text: type: string minLength: 1 maxLength: 500000 description: The text content to be converted to speech. voice: type: string enum: - Alex - Ashley - Craig - Deborah - Dennis - Dominus - Edward - Elizabeth - Hades - Heitor - Julia - Maitê - Mark - Olivia - Pixie - Priya - Ronald - Sarah - Shaun - Theodore - Timothy - Wendy default: Alex description: Name of the voice to be used. format: type: string enum: - wav - mp3 default: mp3 description: >- Audio output format. WAV delivers uncompressed audio in a widely supported container format, while MP3 provides good compression and compatibility. required: - model - text Minimax.v2.TextToSpeechPayloadDTO: type: object properties: model: type: string enum: - minimax/speech-2.5-turbo-preview - minimax/speech-2.5-hd-preview - minimax/speech-2.6-hd - minimax/speech-2.6-turbo description: TTS model to use for synthesis text: type: string minLength: 1 maxLength: 5000 description: The text content to be converted to speech. voice_setting: type: object properties: voice_id: anyOf: - type: string enum: &ref_70 - Wise_Woman - Friendly_Person - Inspirational_girl - Deep_Voice_Man - Calm_Woman - Casual_Guy - Lively_Girl - Patient_Man - Young_Knight - Determined_Man - Lovely_Girl - Decent_Boy - Imposing_Manner - Elegant_Man - Abbess - Sweet_Girl_2 - Exuberant_Girl - type: string minLength: 1 maxLength: 64 default: Wise_Woman description: A predefined system voice for text-to-speech synthesis. speed: type: number minimum: 0.5 maximum: 2 default: 1 description: >- Adjusts the speed of the voice. A value of 1.0 is the default speed, while values less than 1.0 slow down the speech, and values greater than 1.0 speed it up. vol: type: number minimum: 0.01 maximum: 10 default: 1 description: >- The volume of the generated speech. Range: (0, 10]. Larger values indicate larger volumes. pitch: type: number minimum: -12 maximum: 12 default: 0 description: >- The pitch of the generated speech. Range: [-12, 12]. 0 = default voice output. emotion: type: string enum: - happy - sad - angry - fearful - disgusted - surprised - neutral description: >- Emotional tone to apply to the synthesized speech. Controls the emotional expression of the generated voice output. text_normalization: type: boolean default: false description: >- English text normalization support. Improves number-reading but increases latency. default: voice_id: Wise_Woman description: >- Voice settings overriding stored settings for the given voice. They are applied only on the given request. audio_setting: type: object properties: sample_rate: type: integer description: Audio sample rate in Hz. enum: - 8000 - 16000 - 22050 - 24000 - 32000 - 44100 bitrate: type: integer description: >- Audio bitrate in bits per second. Controls the compression level and audio quality. Higher bitrates provide better quality but larger file sizes. enum: - 32000 - 64000 - 128000 - 256000 format: type: string enum: - mp3 - pcm - flac default: mp3 description: >- Audio output format. MP3 provides good compression and compatibility, PCM offers uncompressed high quality, and FLAC provides lossless compression. channel: type: integer description: >- Number of audio channels. 1 for mono (single channel), 2 for stereo (dual channel) output. enum: - 1 - 2 description: Audio output configuration pronunciation_dict: type: object properties: tone: type: array items: type: string description: >- Replacement of text and pronunciations. Format: ["燕少飞/(yan4)(shao3)(fei1)", "达菲/(da2)(fei1)", "omg/oh my god"] required: - tone description: >- Custom pronunciation dictionary for handling specific words or phrases. Allows fine-tuning of how certain text should be pronounced using phonetic representations. timbre_weights: type: array items: type: object properties: voice_id: anyOf: - type: string enum: *ref_70 - type: string minLength: 1 maxLength: 64 description: A predefined system voice for text-to-speech synthesis. weight: type: integer minimum: 1 maximum: 100 description: >- Weight for voice mixing. Range: [1, 100]. Higher weights are sampled more heavily. required: - voice_id - weight maxItems: 4 description: >- Voice mixing configuration allowing combination of up to 4 different voices with specified weights. Each voice contributes to the final output based on its weight value (1-100). stream: type: boolean default: false description: >- Enable streaming mode for real-time audio generation. When enabled, audio is generated and delivered in chunks as it's processed. language_boost: type: string enum: - Chinese - Chinese,Yue - English - Arabic - Russian - Spanish - French - Portuguese - German - Turkish - Dutch - Ukrainian - Vietnamese - Indonesian - Japanese - Italian - Korean - Thai - Polish - Romanian - Greek - Czech - Finnish - Hindi - Bulgarian - Danish - Hebrew - Malay - Persian - Slovak - Swedish - Croatian - Filipino - Hungarian - Norwegian - Slovenian - Catalan - Nynorsk - Tamil - Afrikaans - auto description: Language recognition enhancement option. voice_modify: type: object properties: pitch: type: integer minimum: -100 maximum: 100 description: Pitch level (-100 to 100) intensity: type: integer minimum: -100 maximum: 100 description: Intensity level (-100 to 100) timbre: type: integer minimum: -100 maximum: 100 description: Timbre level (-100 to 100) sound_effects: type: string enum: - spacious_echo - auditorium_echo - lofi_telephone - robotic description: >- Audio effects to apply to the synthesized speech. Includes options like spacious_echo, auditorium_echo, lofi_telephone, and robotic effects. description: >- Voice modification settings for adjusting pitch, intensity, timbre, and applying sound effects to customize the voice characteristics. subtitle_enable: type: boolean default: false description: >- Enable subtitle generation service. Only available for non-streaming requests. Generates timing information for the synthesized speech. output_format: type: string enum: - url - hex default: hex description: >- Format of the output content for non-streaming requests. Controls how the generated audio data is encoded in the response. required: - model - text Embedding.v1.CreateEmbeddingsDTO: oneOf: - type: object properties: model: type: string enum: - text-embedding-3-small - text-embedding-3-large - text-embedding-ada-002 input: anyOf: - type: string minLength: 1 - type: array items: type: string minItems: 1 description: Input text to embed, encoded as a string or array of tokens. encoding_format: type: string nullable: true enum: - float - base64 default: float description: The format in which to return the embeddings. dimensions: type: number nullable: true description: The number of dimensions for the embedding. Default is 1024. required: - model - input additionalProperties: false - type: object properties: model: type: string enum: - voyage-large-2-instruct - voyage-finance-2 - voyage-multilingual-2 - voyage-law-2 - voyage-code-2 - voyage-large-2 - voyage-2 input: anyOf: - type: string minLength: 1 maxLength: 8000 - type: array items: type: string maxLength: 800 description: Input text to embed, encoded as a string or array of tokens. input_type: type: string enum: - document default: document description: The type of input data for the model. required: - model - input - type: object properties: model: type: string enum: - togethercomputer/m2-bert-80M-32k-retrieval input: anyOf: - type: string minLength: 1 - type: array items: type: string minItems: 1 description: Input text to embed, encoded as a string or array of tokens. required: - model - input - type: object properties: model: type: string enum: - text-multilingual-embedding-002 input: anyOf: - type: string minLength: 1 - type: array items: type: string minItems: 1 description: Input text to embed, encoded as a string or array of tokens. dimensions: type: number nullable: true description: The number of dimensions for the embedding. Default is 1024. auto_truncate: type: boolean default: true description: >- If enabled, this parameter automatically truncates the input text to fit within the model’s maximum token limit. It helps ensure that longer texts are processed without errors. task_type: type: string enum: - RETRIEVAL_QUERY - RETRIEVAL_DOCUMENT - SEMANTIC_SIMILARITY - CLASSIFICATION - CLUSTERING - QUESTION_ANSWERING - FACT_VERIFICATION description: Optional task type for which the embeddings will be used. title: type: string description: >- An optional title for the text. Only applicable when task_type is RETRIEVAL_DOCUMENT. Note: Specifying a title for RETRIEVAL_DOCUMENT provides better quality embeddings for retrieval. required: - model - input - type: object properties: model: type: string enum: - alibaba/qwen-text-embedding-v4 - alibaba/qwen-text-embedding-v3 input: anyOf: - type: string minLength: 1 - type: array items: type: string minItems: 1 description: Input text to embed, encoded as a string or array of tokens. dimensions: type: integer minimum: 64 maximum: 2048 default: 1024 description: The number of dimensions for the embedding. Default is 1024. required: - model - input Embedding.v1.CreateEmbeddingsResponseDTO: type: object properties: object: type: string enum: - object data: type: array items: type: object properties: object: type: string enum: - embedding index: type: number embedding: type: array items: type: number required: - object - index - embedding model: type: string usage: type: object properties: total_tokens: type: number nullable: true required: - object - data - model - usage Vision.v1.OCRPayloadDTO: anyOf: - $ref: '#/components/schemas/Vision.v1.OCRGoogleRequestDTO' - $ref: '#/components/schemas/Vision.v1.OCRMistralRequestDTO' - $ref: '#/components/schemas/Vision.v1.OCRZhipuRequestDTO' Vision.v1.OCRGoogleRequestDTO: type: object properties: model: type: string enum: - google/gc-document-ai default: google/gc-document-ai deprecated: true document: anyOf: - type: string format: uri - type: string description: The document file to be processed by the OCR model. mimeType: type: string enum: - application/pdf - image/gif - image/tiff - image/jpeg - image/png - image/bmp - image/webp - text/html description: The MIME type of the document. pages: anyOf: - type: object properties: type: type: string enum: - start start: type: integer minimum: 1 required: - type - start - type: object properties: type: type: string enum: - end end: type: integer minimum: 1 required: - type - end - type: object properties: type: type: string enum: - range start: type: integer minimum: 1 end: type: integer minimum: 2 required: - type - start - end - type: object properties: type: type: string enum: - indices indices: type: array items: type: integer minimum: 1 maxItems: 15 required: - type - indices description: Specific pages you wants to process required: - document additionalProperties: false Vision.v1.OCRMistralRequestDTO: type: object properties: model: type: string enum: - mistral/mistral-ocr-latest default: mistral/mistral-ocr-latest description: Model ID document: oneOf: - type: object properties: type: type: string enum: - document_url description: Type of document. document_url: type: string format: uri description: Document URL. required: - type - document_url - type: object properties: type: type: string enum: - image_url description: Image URL. image_url: type: string format: uri description: Type of document. required: - type - image_url description: Document to run OCR pages: anyOf: - type: string - type: array items: type: integer - nullable: true description: Specific pages you wants to process example: '"3" or "0-2" or [0, 3, 4]' include_image_base64: type: boolean nullable: true description: Include base64 images in response image_limit: type: integer nullable: true description: Max images to extract image_min_size: type: integer nullable: true description: Minimum height and width of image to extract required: - document Vision.v1.OCRZhipuRequestDTO: type: object properties: model: type: string enum: - zhipu/glm-ocr default: zhipu/glm-ocr description: Model ID document: oneOf: - type: object properties: type: type: string enum: - document_url description: Type of document. document_url: type: string format: uri description: >- URL of a document file to be processed by the OCR model. Supported file formats: PDF ≤ 50MB. required: - type - document_url - type: object properties: type: type: string enum: - image_url description: Image URL. image_url: type: string format: uri description: >- URL of a single image to be processed by the OCR model. Supported file formats: JPG, PNG. Single image ≤10MB. required: - type - image_url description: Document to run OCR. pages: anyOf: - type: string - type: array items: type: integer - nullable: true description: Specific pages to process, e.g. "3", "0-2", [0, 3, 4]. include_image_base64: type: boolean nullable: true description: Include base64 images in response. image_limit: type: integer nullable: true description: Max images to extract. image_min_size: type: integer nullable: true description: Minimum height and width of image to extract. return_crop_images: type: boolean nullable: true description: Whether to return screenshot information need_layout_visualization: type: boolean nullable: true description: Whether to return detailed layout image result information required: - document Model.v1.ModelsResponseDto: type: object properties: object: type: string data: type: array items: $ref: '#/components/schemas/Model.v1.ModelListItemDto' required: - object - data Model.v1.ModelListItemDto: type: object properties: id: type: string description: name of model type: type: string info: $ref: '#/components/schemas/Model.v1.ModelInfoDto' features: type: array items: type: string required: - id - type - info - features Model.v1.ModelInfoDto: type: object properties: name: type: string developer: type: string description: type: string contextLength: type: number url: type: string required: - name - developer - description - contextLength - url Model.v1.ModelDetailedDto: type: object properties: name: type: string provider: type: string type: type: string info: $ref: '#/components/schemas/Model.v1.ModelInfoDto' features: type: array items: type: string tags: type: array items: type: string isPremium: type: boolean isFree: type: boolean required: - name - provider - type - info - features - tags - isPremium - isFree