openapi: 3.2.0 info: title: ElevenLabs API Documentation Flows API description: This is the documentation for the ElevenLabs API. You can use this API to use our service programmatically, this is done by using your API key. You can find your API key in the dashboard at https://elevenlabs.io/app/settings/api-keys. version: '1.0' tags: - name: Flows paths: /v1/flows/video: post: tags: - Flows summary: Create Video Generation description: Start a video generation with the selected model. operationId: create_video_generation parameters: - name: xi-api-key in: header required: false schema: anyOf: - type: string - type: 'null' description: Your API key. This is required by most endpoints to access our API programmatically. You can view your xi-api-key using the 'Profile' tab on the website. title: Xi-Api-Key description: Your API key. This is required by most endpoints to access our API programmatically. You can view your xi-api-key using the 'Profile' tab on the website. requestBody: required: true content: application/json: schema: $ref: '#/components/schemas/VideoGenerationRequest' responses: '200': description: Successful Response content: application/json: schema: $ref: '#/components/schemas/MediaGenerationCreateResponse' '422': description: Validation Error content: application/json: schema: $ref: '#/components/schemas/HTTPValidationError' x-fern-sdk-group-name: - flows - video x-fern-sdk-method-name: create get: tags: - Flows summary: List Video Generations description: List the video generations created through this API, newest first. operationId: list_video_generations parameters: - name: cursor in: query required: false schema: anyOf: - type: string - type: 'null' description: 'Pagination cursor: the `next_cursor` value of the previous page''s response. Omit it for the first page.' title: Cursor description: 'Pagination cursor: the `next_cursor` value of the previous page''s response. Omit it for the first page.' - name: page_size in: query required: false schema: type: integer maximum: 100 minimum: 1 description: How many generations to return per page. default: 30 title: Page Size description: How many generations to return per page. - name: status in: query required: false schema: anyOf: - enum: - pending - generating - completed - failed type: string - type: 'null' description: Only return generations with this lifecycle status. title: Status description: Only return generations with this lifecycle status. - name: model_id in: query required: false schema: anyOf: - type: string - type: 'null' description: Only return generations of this model. title: Model Id description: Only return generations of this model. - name: xi-api-key in: header required: false schema: anyOf: - type: string - type: 'null' description: Your API key. This is required by most endpoints to access our API programmatically. You can view your xi-api-key using the 'Profile' tab on the website. title: Xi-Api-Key description: Your API key. This is required by most endpoints to access our API programmatically. You can view your xi-api-key using the 'Profile' tab on the website. responses: '200': description: Successful Response content: application/json: schema: $ref: '#/components/schemas/MediaGenerationListResponse' '422': description: Validation Error content: application/json: schema: $ref: '#/components/schemas/HTTPValidationError' x-fern-sdk-group-name: - flows - video x-fern-sdk-method-name: list /v1/flows/video/{generation_id}: get: tags: - Flows summary: Get Video Generation description: Retrieve the status of a video generation, and retrieve its output URL once completed. operationId: get_video_generation parameters: - name: generation_id in: path required: true schema: type: string title: Generation Id - name: xi-api-key in: header required: false schema: anyOf: - type: string - type: 'null' description: Your API key. This is required by most endpoints to access our API programmatically. You can view your xi-api-key using the 'Profile' tab on the website. title: Xi-Api-Key description: Your API key. This is required by most endpoints to access our API programmatically. You can view your xi-api-key using the 'Profile' tab on the website. responses: '200': description: Successful Response content: application/json: schema: $ref: '#/components/schemas/MediaGenerationResponse' '422': description: Validation Error content: application/json: schema: $ref: '#/components/schemas/HTTPValidationError' x-fern-sdk-group-name: - flows - video x-fern-sdk-method-name: get /v1/flows/image: post: tags: - Flows summary: Create Image Generation description: Start an image generation with the selected model. operationId: create_image_generation parameters: - name: xi-api-key in: header required: false schema: anyOf: - type: string - type: 'null' description: Your API key. This is required by most endpoints to access our API programmatically. You can view your xi-api-key using the 'Profile' tab on the website. title: Xi-Api-Key description: Your API key. This is required by most endpoints to access our API programmatically. You can view your xi-api-key using the 'Profile' tab on the website. requestBody: required: true content: application/json: schema: $ref: '#/components/schemas/ImageGenerationRequest' responses: '200': description: Successful Response content: application/json: schema: $ref: '#/components/schemas/MediaGenerationCreateResponse' '422': description: Validation Error content: application/json: schema: $ref: '#/components/schemas/HTTPValidationError' x-fern-sdk-group-name: - flows - image x-fern-sdk-method-name: create get: tags: - Flows summary: List Image Generations description: List the image generations created through this API, newest first. operationId: list_image_generations parameters: - name: cursor in: query required: false schema: anyOf: - type: string - type: 'null' description: 'Pagination cursor: the `next_cursor` value of the previous page''s response. Omit it for the first page.' title: Cursor description: 'Pagination cursor: the `next_cursor` value of the previous page''s response. Omit it for the first page.' - name: page_size in: query required: false schema: type: integer maximum: 100 minimum: 1 description: How many generations to return per page. default: 30 title: Page Size description: How many generations to return per page. - name: status in: query required: false schema: anyOf: - enum: - pending - generating - completed - failed type: string - type: 'null' description: Only return generations with this lifecycle status. title: Status description: Only return generations with this lifecycle status. - name: model_id in: query required: false schema: anyOf: - type: string - type: 'null' description: Only return generations of this model. title: Model Id description: Only return generations of this model. - name: xi-api-key in: header required: false schema: anyOf: - type: string - type: 'null' description: Your API key. This is required by most endpoints to access our API programmatically. You can view your xi-api-key using the 'Profile' tab on the website. title: Xi-Api-Key description: Your API key. This is required by most endpoints to access our API programmatically. You can view your xi-api-key using the 'Profile' tab on the website. responses: '200': description: Successful Response content: application/json: schema: $ref: '#/components/schemas/MediaGenerationListResponse' '422': description: Validation Error content: application/json: schema: $ref: '#/components/schemas/HTTPValidationError' x-fern-sdk-group-name: - flows - image x-fern-sdk-method-name: list /v1/flows/image/{generation_id}: get: tags: - Flows summary: Get Image Generation description: Retrieve the status of an image generation, and retrieve its output URL once completed. operationId: get_image_generation parameters: - name: generation_id in: path required: true schema: type: string title: Generation Id - name: xi-api-key in: header required: false schema: anyOf: - type: string - type: 'null' description: Your API key. This is required by most endpoints to access our API programmatically. You can view your xi-api-key using the 'Profile' tab on the website. title: Xi-Api-Key description: Your API key. This is required by most endpoints to access our API programmatically. You can view your xi-api-key using the 'Profile' tab on the website. responses: '200': description: Successful Response content: application/json: schema: $ref: '#/components/schemas/MediaGenerationResponse' '422': description: Validation Error content: application/json: schema: $ref: '#/components/schemas/HTTPValidationError' x-fern-sdk-group-name: - flows - image x-fern-sdk-method-name: get /v1/flows/text-to-speech: post: tags: - Flows summary: Create Speech Generation description: Start a speech generation with the selected model. Charged per character via text-to-speech billing. Use this over `/v1/text-to-speech` for the asynchronous generation lifecycle or for models not offered there; for direct, synchronous speech synthesis, prefer `/v1/text-to-speech`. operationId: create_text_to_speech_generation parameters: - name: xi-api-key in: header required: false schema: anyOf: - type: string - type: 'null' description: Your API key. This is required by most endpoints to access our API programmatically. You can view your xi-api-key using the 'Profile' tab on the website. title: Xi-Api-Key description: Your API key. This is required by most endpoints to access our API programmatically. You can view your xi-api-key using the 'Profile' tab on the website. requestBody: required: true content: application/json: schema: $ref: '#/components/schemas/TextToSpeechGenerationRequest' responses: '200': description: Successful Response content: application/json: schema: $ref: '#/components/schemas/MediaGenerationCreateResponse' '422': description: Validation Error content: application/json: schema: $ref: '#/components/schemas/HTTPValidationError' x-fern-sdk-group-name: - flows - text_to_speech x-fern-sdk-method-name: create get: tags: - Flows summary: List Speech Generations description: List the speech generations created through this API, newest first. operationId: list_text_to_speech_generations parameters: - name: cursor in: query required: false schema: anyOf: - type: string - type: 'null' description: 'Pagination cursor: the `next_cursor` value of the previous page''s response. Omit it for the first page.' title: Cursor description: 'Pagination cursor: the `next_cursor` value of the previous page''s response. Omit it for the first page.' - name: page_size in: query required: false schema: type: integer maximum: 100 minimum: 1 description: How many generations to return per page. default: 30 title: Page Size description: How many generations to return per page. - name: status in: query required: false schema: anyOf: - enum: - pending - generating - completed - failed type: string - type: 'null' description: Only return generations with this lifecycle status. title: Status description: Only return generations with this lifecycle status. - name: model_id in: query required: false schema: anyOf: - type: string - type: 'null' description: Only return generations of this model. title: Model Id description: Only return generations of this model. - name: xi-api-key in: header required: false schema: anyOf: - type: string - type: 'null' description: Your API key. This is required by most endpoints to access our API programmatically. You can view your xi-api-key using the 'Profile' tab on the website. title: Xi-Api-Key description: Your API key. This is required by most endpoints to access our API programmatically. You can view your xi-api-key using the 'Profile' tab on the website. responses: '200': description: Successful Response content: application/json: schema: $ref: '#/components/schemas/MediaGenerationListResponse' '422': description: Validation Error content: application/json: schema: $ref: '#/components/schemas/HTTPValidationError' x-fern-sdk-group-name: - flows - text_to_speech x-fern-sdk-method-name: list /v1/flows/text-to-speech/{generation_id}: get: tags: - Flows summary: Get Speech Generation description: Retrieve the status of a speech generation, and retrieve its output URL once completed. operationId: get_text_to_speech_generation parameters: - name: generation_id in: path required: true schema: type: string title: Generation Id - name: xi-api-key in: header required: false schema: anyOf: - type: string - type: 'null' description: Your API key. This is required by most endpoints to access our API programmatically. You can view your xi-api-key using the 'Profile' tab on the website. title: Xi-Api-Key description: Your API key. This is required by most endpoints to access our API programmatically. You can view your xi-api-key using the 'Profile' tab on the website. responses: '200': description: Successful Response content: application/json: schema: $ref: '#/components/schemas/MediaGenerationResponse' '422': description: Validation Error content: application/json: schema: $ref: '#/components/schemas/HTTPValidationError' x-fern-sdk-group-name: - flows - text_to_speech x-fern-sdk-method-name: get components: schemas: MediaGenerationFailedResponse: properties: id: type: string title: Id description: The unique identifier of the generation. examples: - JWr5N6X9ZTqf8jD2LmQb status: type: string const: failed title: Status description: The lifecycle status of the generation. examples: - failed failure_reason: type: string enum: - timeout - model_error - moderated - invalid_parameters - dependency_failed - charging_failed - internal_error title: Failure Reason description: The category of failure. examples: - timeout error_message: type: string title: Error Message description: A human-readable description of the failure. Failed generations are not charged. examples: - Timed out while processing. You were not charged for this generation. type: object required: - id - status - failure_reason - error_message title: MediaGenerationFailedResponse description: A failed media generation and why it failed. example: error_message: Timed out while processing. You were not charged for this generation. failure_reason: timeout id: JWr5N6X9ZTqf8jD2LmQb status: failed ImageGenerationRequest: oneOf: - $ref: '#/components/schemas/GPTImage1Request' - $ref: '#/components/schemas/GPTImage1_5Request' - $ref: '#/components/schemas/GPTImage2Request' - $ref: '#/components/schemas/Gemini25FlashImageRequest' - $ref: '#/components/schemas/Gemini3ProImageRequest' - $ref: '#/components/schemas/Gemini31FlashImageRequest' - $ref: '#/components/schemas/Gemini31FlashLiteImageRequest' - $ref: '#/components/schemas/BytedanceSeedream5LiteRequest' - $ref: '#/components/schemas/BytedanceSeedream5ProRequest' discriminator: propertyName: model_id mapping: bytedance-seedream-5-lite: '#/components/schemas/BytedanceSeedream5LiteRequest' bytedance-seedream-5-pro: '#/components/schemas/BytedanceSeedream5ProRequest' gemini-2.5-flash-image: '#/components/schemas/Gemini25FlashImageRequest' gemini-3-pro-image: '#/components/schemas/Gemini3ProImageRequest' gemini-3.1-flash-image: '#/components/schemas/Gemini31FlashImageRequest' gemini-3.1-flash-lite-image: '#/components/schemas/Gemini31FlashLiteImageRequest' gpt-image-1: '#/components/schemas/GPTImage1Request' gpt-image-1.5: '#/components/schemas/GPTImage1_5Request' gpt-image-2: '#/components/schemas/GPTImage2Request' InlineImageReference: properties: type: type: string const: inline_base64 title: Type content_base64: type: string maxLength: 34952536 title: Content Base64 description: The media file's bytes, base64-encoded (standard alphabet). Up to 25MB decoded. examples: - iVBORw0KGgoAAAANSUhEUgAA... mime_type: type: string enum: - image/jpeg - image/png - image/webp - image/heic - image/heif title: Mime Type description: The MIME type of the encoded image. additionalProperties: false type: object required: - type - content_base64 - mime_type title: InlineImageReference description: 'An image passed inline as base64. The image is stored as an ephemeral asset with no guaranteed retention: it may be deleted at any time after the generation completes. To keep an input and reuse it across generations, upload it via the assets API (`POST /v1/assets`) and pass an `asset` reference instead.' StaticAssetReference: properties: type: type: string const: asset title: Type asset_id: type: string title: Asset Id description: The ID of an asset uploaded via the assets API (`POST /v1/assets`), as returned in that response's `asset_id`. examples: - 5xM2KqOnZyce22SPZ9d4 additionalProperties: false type: object required: - type - asset_id title: StaticAssetReference description: An asset uploaded via the assets API. ValidationError: properties: loc: items: anyOf: - type: string - type: integer type: array title: Location msg: type: string title: Message type: type: string title: Error Type type: object required: - loc - msg - type title: ValidationError MediaGenerationCompletedResponse: properties: id: type: string title: Id description: The unique identifier of the generation. examples: - JWr5N6X9ZTqf8jD2LmQb status: type: string const: completed title: Status description: The lifecycle status of the generation. examples: - completed content_url: type: string title: Content Url description: A signed URL to download the generated media from. It expires about an hour after this response is returned; fetch the generation again for a fresh URL. examples: - https://storage.googleapis.com/generations/JWr5N6X9ZTqf8jD2LmQb content_mime_type: type: string title: Content Mime Type description: The MIME type of the generated media. examples: - video/mp4 - image/png - audio/mpeg type: object required: - id - status - content_url - content_mime_type title: MediaGenerationCompletedResponse description: A completed media generation and its output. example: content_mime_type: video/mp4 content_url: https://storage.googleapis.com/generations/JWr5N6X9ZTqf8jD2LmQb id: JWr5N6X9ZTqf8jD2LmQb status: completed InlineVideoReference: properties: type: type: string const: inline_base64 title: Type content_base64: type: string maxLength: 34952536 title: Content Base64 description: The media file's bytes, base64-encoded (standard alphabet). Up to 25MB decoded. examples: - iVBORw0KGgoAAAANSUhEUgAA... mime_type: type: string enum: - video/mp4 - video/quicktime - video/webm title: Mime Type description: The MIME type of the encoded video. additionalProperties: false type: object required: - type - content_base64 - mime_type title: InlineVideoReference description: 'A video passed inline as base64. The video is stored as an ephemeral asset with no guaranteed retention: it may be deleted at any time after the generation completes. To keep an input and reuse it across generations, upload it via the assets API (`POST /v1/assets`) and pass an `asset` reference instead.' BytedanceSeedance25Request: properties: webhook: anyOf: - $ref: '#/components/schemas/WebhookTarget' - type: 'null' description: Include to send the generation's result to the workspace's configured flows webhooks once it completes or fails. The webhook payload matches the terminal response of the corresponding GET endpoint. examples: - type: all - ids: - Q8mVr2LpXcT4nB6yJdKw type: ids model_id: type: string const: bytedance-seedance-v2.5 title: Model Id description: The model to use for the generation. prompt: type: string title: Prompt description: A text description of the video to generate. examples: - A corgi rides a tiny surfboard across a sunlit wave at golden hour, cinematic aspect_ratio: type: string enum: - auto - '21:9' - '16:9' - '4:3' - '1:1' - '3:4' - '9:16' title: Aspect Ratio description: The aspect ratio of the output video. With `auto`, the model picks an aspect ratio based on the inputs. First-frame / first-and-last-frame tasks always use `auto`. default: '16:9' resolution: type: string enum: - 480p - 720p - 1080p title: Resolution description: The resolution of the output video. default: 720p duration_secs: type: integer maximum: 30.0 minimum: 4.0 title: Duration Secs description: The duration of the output video in seconds. default: 5 generate_audio: type: boolean title: Generate Audio description: Whether to generate audio with the video. default: true start_frame: anyOf: - $ref: '#/components/schemas/ImageReference' - type: 'null' description: The image to use as the video's first frame. end_frame: anyOf: - $ref: '#/components/schemas/ImageReference' - type: 'null' description: The image to use as the video's last frame. images: items: $ref: '#/components/schemas/ImageReference' type: array maxItems: 30 title: Images description: Up to 30 reference images to draw subjects from. Cannot be combined with `start_frame`/`end_frame`. videos: items: $ref: '#/components/schemas/VideoReference' type: array maxItems: 10 title: Videos description: Up to 10 reference videos to draw subjects or motion from. Cannot be combined with `start_frame`/`end_frame`. audios: items: $ref: '#/components/schemas/AudioReference' type: array maxItems: 10 title: Audios description: Up to 10 reference audios, e.g. for lipsync. Cannot be combined with `start_frame`/`end_frame`. additionalProperties: false type: object required: - model_id - prompt title: BytedanceSeedance25Request description: 'Request body for the ByteDance Seedance 2.5 video model. Diverges from the Seedance 2.0 public shape: no 4K, durations up to 30s, larger reference caps, audio-only input allowed, and no ``seed`` (Ark tolerates it but does not honour it). ByteDance models are disabled by default and require explicit approval before use. Contact support to request access.' Gemini31FlashLiteImageRequest: properties: webhook: anyOf: - $ref: '#/components/schemas/WebhookTarget' - type: 'null' description: Include to send the generation's result to the workspace's configured flows webhooks once it completes or fails. The webhook payload matches the terminal response of the corresponding GET endpoint. examples: - type: all - ids: - Q8mVr2LpXcT4nB6yJdKw type: ids prompt: type: string title: Prompt description: A text description of the image to generate. examples: - A corgi in a tiny lifeguard chair on a sunlit beach at golden hour, photorealistic model_id: type: string const: gemini-3.1-flash-lite-image title: Model Id description: The model to use for the generation. images: items: $ref: '#/components/schemas/ImageReference' type: array maxItems: 14 title: Images description: Up to 14 reference images to edit or draw from. aspect_ratio: type: string enum: - auto - '1:1' - '2:3' - '3:2' - '3:4' - '4:3' - '4:5' - '5:4' - '9:16' - '16:9' - '21:9' title: Aspect Ratio description: The aspect ratio of the output image. With `auto`, the model picks an aspect ratio based on the inputs. default: '16:9' resolution: type: string const: 1K title: Resolution description: The resolution of the output image. default: 1K additionalProperties: false type: object required: - prompt - model_id title: Gemini31FlashLiteImageRequest description: Request body for the Google Gemini 3.1 Flash Lite image model. MediaGenerationResponse: oneOf: - $ref: '#/components/schemas/MediaGenerationInProgressResponse' - $ref: '#/components/schemas/MediaGenerationCompletedResponse' - $ref: '#/components/schemas/MediaGenerationFailedResponse' discriminator: propertyName: status mapping: completed: '#/components/schemas/MediaGenerationCompletedResponse' failed: '#/components/schemas/MediaGenerationFailedResponse' generating: '#/components/schemas/MediaGenerationInProgressResponse' pending: '#/components/schemas/MediaGenerationInProgressResponse' WebhookTarget: oneOf: - $ref: '#/components/schemas/WebhookTargetAll' - $ref: '#/components/schemas/WebhookTargetIds' discriminator: propertyName: type mapping: all: '#/components/schemas/WebhookTargetAll' ids: '#/components/schemas/WebhookTargetIds' VideoGenerationRequest: oneOf: - $ref: '#/components/schemas/CreatifyAuroraRequest' - $ref: '#/components/schemas/Veo3_1Request' - $ref: '#/components/schemas/Veo3_1FastRequest' - $ref: '#/components/schemas/BytedanceSeedance2Request' - $ref: '#/components/schemas/BytedanceSeedance2FastRequest' - $ref: '#/components/schemas/BytedanceSeedance2MiniRequest' - $ref: '#/components/schemas/BytedanceSeedance25Request' discriminator: propertyName: model_id mapping: bytedance-seedance-v2: '#/components/schemas/BytedanceSeedance2Request' bytedance-seedance-v2-fast: '#/components/schemas/BytedanceSeedance2FastRequest' bytedance-seedance-v2-mini: '#/components/schemas/BytedanceSeedance2MiniRequest' bytedance-seedance-v2.5: '#/components/schemas/BytedanceSeedance25Request' creatify-aurora: '#/components/schemas/CreatifyAuroraRequest' veo-3.1-fast-generate-001: '#/components/schemas/Veo3_1FastRequest' veo-3.1-generate-001: '#/components/schemas/Veo3_1Request' Veo3_1Request: properties: webhook: anyOf: - $ref: '#/components/schemas/WebhookTarget' - type: 'null' description: Include to send the generation's result to the workspace's configured flows webhooks once it completes or fails. The webhook payload matches the terminal response of the corresponding GET endpoint. examples: - type: all - ids: - Q8mVr2LpXcT4nB6yJdKw type: ids prompt: type: string title: Prompt description: A text description of the video to generate. examples: - A corgi rides a tiny surfboard across a sunlit wave at golden hour, cinematic negative_prompt: anyOf: - type: string - type: 'null' title: Negative Prompt description: A text description of what the video should avoid. seed: anyOf: - type: integer - type: 'null' title: Seed description: 'A seed for reproducible generation: the same seed and inputs give similar output across generations. Omit for random.' enhance_prompt: type: boolean title: Enhance Prompt description: Whether the model may rewrite the prompt to improve results. default: true duration_secs: type: integer enum: - 4 - 6 - 8 title: Duration Secs description: The duration of the output video in seconds. default: 8 aspect_ratio: type: string enum: - '16:9' - '9:16' title: Aspect Ratio description: The aspect ratio of the output video. default: '16:9' resolution: type: string enum: - 720p - 1080p - 4K title: Resolution description: The resolution of the output video. default: 720p generate_audio: type: boolean title: Generate Audio description: Whether to generate audio with the video. default: true start_frame: anyOf: - $ref: '#/components/schemas/ImageReference' - type: 'null' description: The image to use as the video's first frame. end_frame: anyOf: - $ref: '#/components/schemas/ImageReference' - type: 'null' description: The image to use as the video's last frame. images: items: $ref: '#/components/schemas/VeoImageReference' type: array maxItems: 3 title: Images description: Up to 3 reference images to draw subjects or style from. Cannot be combined with `start_frame`/`end_frame`, and requires the 8-second duration. model_id: type: string const: veo-3.1-generate-001 title: Model Id description: The model to use for the generation. additionalProperties: false type: object required: - prompt - model_id title: Veo3_1Request description: Request body for the Google Veo 3.1 video model. ElevenV3Request: properties: webhook: anyOf: - $ref: '#/components/schemas/WebhookTarget' - type: 'null' description: Include to send the generation's result to the workspace's configured flows webhooks once it completes or fails. The webhook payload matches the terminal response of the corresponding GET endpoint. examples: - type: all - ids: - Q8mVr2LpXcT4nB6yJdKw type: ids text: type: string title: Text description: The text to synthesize into speech. examples: - The first move is what sets everything in motion. voice: type: string title: Voice description: The ID of the voice to speak with. examples: - JBFqnCBsd6RMkjVDRZzb output_format: type: string enum: - mp3_22050_32 - mp3_24000_48 - mp3_44100_32 - mp3_44100_64 - mp3_44100_96 - mp3_44100_128 - mp3_44100_192 title: Output Format description: The audio encoding of the output, as `codec_sampleRateHz_bitrateKbps`. `mp3_44100_192` requires the Creator tier or above. default: mp3_44100_128 pronunciation_dictionary_locators: items: $ref: '#/components/schemas/PronunciationDictionaryVersionLocator' type: array maxItems: 3 title: Pronunciation Dictionary Locators description: Pronunciation dictionaries to apply to the text, in order of precedence. Up to 3. model_id: type: string const: eleven_v3 title: Model Id description: The model to use for the generation. language_code: anyOf: - type: string - type: 'null' title: Language Code description: ISO 639-1 language code to enforce on the output. Omit to detect the language from the text. examples: - en voice_settings: anyOf: - $ref: '#/components/schemas/ElevenV3VoiceSettings' - type: 'null' description: Overrides for the voice's saved settings, applied to this generation only. additionalProperties: false type: object required: - text - voice - model_id title: ElevenV3Request description: Request body for the Eleven v3 TTS model. Gemini31FlashImageRequest: properties: webhook: anyOf: - $ref: '#/components/schemas/WebhookTarget' - type: 'null' description: Include to send the generation's result to the workspace's configured flows webhooks once it completes or fails. The webhook payload matches the terminal response of the corresponding GET endpoint. examples: - type: all - ids: - Q8mVr2LpXcT4nB6yJdKw type: ids prompt: type: string title: Prompt description: A text description of the image to generate. examples: - A corgi in a tiny lifeguard chair on a sunlit beach at golden hour, photorealistic model_id: type: string const: gemini-3.1-flash-image title: Model Id description: The model to use for the generation. images: items: $ref: '#/components/schemas/ImageReference' type: array maxItems: 14 title: Images description: Up to 14 reference images to edit or draw from. aspect_ratio: type: string enum: - auto - '1:1' - '2:3' - '3:2' - '3:4' - '4:3' - '4:5' - '5:4' - '9:16' - '16:9' - '21:9' - '1:4' - '4:1' - '1:8' - '8:1' title: Aspect Ratio description: The aspect ratio of the output image. With `auto`, the model picks an aspect ratio based on the inputs. default: '16:9' resolution: type: string enum: - '512' - 1K - 2K - 4K title: Resolution description: The resolution of the output image. default: 1K additionalProperties: false type: object required: - prompt - model_id title: Gemini31FlashImageRequest description: Request body for the Google Gemini 3.1 Flash image model. AudioReference: oneOf: - $ref: '#/components/schemas/GenerationReference' - $ref: '#/components/schemas/StaticAssetReference' - $ref: '#/components/schemas/InlineAudioReference' discriminator: propertyName: type mapping: asset: '#/components/schemas/StaticAssetReference' generation: '#/components/schemas/GenerationReference' inline_base64: '#/components/schemas/InlineAudioReference' WebhookTargetAll: properties: type: type: string const: all title: Type description: Send the result to all of the workspace's configured flows webhooks. default: all type: object title: WebhookTargetAll description: Deliver the result to all of the workspace's configured flows webhooks. ElevenFlashV2_5Request: properties: webhook: anyOf: - $ref: '#/components/schemas/WebhookTarget' - type: 'null' description: Include to send the generation's result to the workspace's configured flows webhooks once it completes or fails. The webhook payload matches the terminal response of the corresponding GET endpoint. examples: - type: all - ids: - Q8mVr2LpXcT4nB6yJdKw type: ids text: type: string title: Text description: The text to synthesize into speech. examples: - The first move is what sets everything in motion. voice: type: string title: Voice description: The ID of the voice to speak with. examples: - JBFqnCBsd6RMkjVDRZzb output_format: type: string enum: - mp3_22050_32 - mp3_24000_48 - mp3_44100_32 - mp3_44100_64 - mp3_44100_96 - mp3_44100_128 - mp3_44100_192 title: Output Format description: The audio encoding of the output, as `codec_sampleRateHz_bitrateKbps`. `mp3_44100_192` requires the Creator tier or above. default: mp3_44100_128 pronunciation_dictionary_locators: items: $ref: '#/components/schemas/PronunciationDictionaryVersionLocator' type: array maxItems: 3 title: Pronunciation Dictionary Locators description: Pronunciation dictionaries to apply to the text, in order of precedence. Up to 3. model_id: type: string const: eleven_flash_v2_5 title: Model Id description: The model to use for the generation. language_code: anyOf: - type: string - type: 'null' title: Language Code description: ISO 639-1 language code to enforce on the output. Omit to detect the language from the text. examples: - en voice_settings: anyOf: - $ref: '#/components/schemas/ElevenFlashV2_5VoiceSettings' - type: 'null' description: Overrides for the voice's saved settings, applied to this generation only. additionalProperties: false type: object required: - text - voice - model_id title: ElevenFlashV2_5Request description: Request body for the ElevenLabs Flash v2.5 TTS model. InlineAudioReference: properties: type: type: string const: inline_base64 title: Type content_base64: type: string maxLength: 34952536 title: Content Base64 description: The media file's bytes, base64-encoded (standard alphabet). Up to 25MB decoded. examples: - iVBORw0KGgoAAAANSUhEUgAA... mime_type: type: string enum: - audio/mpeg - audio/wav title: Mime Type description: The MIME type of the encoded audio. additionalProperties: false type: object required: - type - content_base64 - mime_type title: InlineAudioReference description: 'Audio passed inline as base64. The audio is stored as an ephemeral asset with no guaranteed retention: it may be deleted at any time after the generation completes. To keep an input and reuse it across generations, upload it via the assets API (`POST /v1/assets`) and pass an `asset` reference instead.' WebhookTargetIds: properties: type: type: string const: ids title: Type description: Send the result to the listed flows webhooks. default: ids ids: items: type: string type: array minItems: 1 title: Ids description: The IDs of the workspace flows webhooks to deliver the result to. Each must be one of the workspace's configured flows webhooks. examples: - - Q8mVr2LpXcT4nB6yJdKw type: object required: - ids title: WebhookTargetIds description: Deliver the result to specific configured flows webhooks. MediaGenerationCreateResponse: properties: id: type: string title: Id description: The unique identifier of the generation. Pass it to the corresponding GET endpoint to retrieve the output. examples: - JWr5N6X9ZTqf8jD2LmQb status: type: string const: pending title: Status description: A newly created generation is always `pending`. examples: - pending type: object required: - id - status title: MediaGenerationCreateResponse description: A newly queued media generation; fetch the GET endpoint for the output. example: id: JWr5N6X9ZTqf8jD2LmQb status: pending GPTImage1_5Request: properties: webhook: anyOf: - $ref: '#/components/schemas/WebhookTarget' - type: 'null' description: Include to send the generation's result to the workspace's configured flows webhooks once it completes or fails. The webhook payload matches the terminal response of the corresponding GET endpoint. examples: - type: all - ids: - Q8mVr2LpXcT4nB6yJdKw type: ids prompt: type: string title: Prompt description: A text description of the image to generate. examples: - A corgi in a tiny lifeguard chair on a sunlit beach at golden hour, photorealistic images: items: $ref: '#/components/schemas/ImageReference' type: array maxItems: 5 title: Images description: Up to 5 reference images to edit or draw from. mask: anyOf: - $ref: '#/components/schemas/ImageReference' - type: 'null' description: An image whose fully transparent areas mark where the first reference image may be edited; requires `images`. quality: type: string enum: - low - medium - high title: Quality description: The quality of the output image. default: medium background: type: string enum: - transparent - opaque - auto title: Background description: The background of the output image. With `auto`, the model picks the background that suits the image. default: auto aspect_ratio: type: string enum: - '1:1' - '3:2' - '2:3' title: Aspect Ratio description: The aspect ratio of the output image. default: '1:1' model_id: type: string const: gpt-image-1.5 title: Model Id description: The model to use for the generation. additionalProperties: false type: object required: - prompt - model_id title: GPTImage1_5Request description: Request body for the OpenAI GPT Image 1.5 model. HTTPValidationError: properties: detail: items: $ref: '#/components/schemas/ValidationError' type: array title: Detail type: object title: HTTPValidationError VeoImageReference: properties: image: $ref: '#/components/schemas/ImageReference' description: The reference image. role: type: string enum: - subject - style title: Role description: 'How the model uses the image: `subject` places its subject or scene elements into the video; `style` transfers its visual style.' additionalProperties: false type: object required: - image - role title: VeoImageReference description: A reference image guiding a Veo generation, with its role. ElevenMultilingualV2Request: properties: webhook: anyOf: - $ref: '#/components/schemas/WebhookTarget' - type: 'null' description: Include to send the generation's result to the workspace's configured flows webhooks once it completes or fails. The webhook payload matches the terminal response of the corresponding GET endpoint. examples: - type: all - ids: - Q8mVr2LpXcT4nB6yJdKw type: ids text: type: string title: Text description: The text to synthesize into speech. examples: - The first move is what sets everything in motion. voice: type: string title: Voice description: The ID of the voice to speak with. examples: - JBFqnCBsd6RMkjVDRZzb output_format: type: string enum: - mp3_22050_32 - mp3_24000_48 - mp3_44100_32 - mp3_44100_64 - mp3_44100_96 - mp3_44100_128 - mp3_44100_192 title: Output Format description: The audio encoding of the output, as `codec_sampleRateHz_bitrateKbps`. `mp3_44100_192` requires the Creator tier or above. default: mp3_44100_128 pronunciation_dictionary_locators: items: $ref: '#/components/schemas/PronunciationDictionaryVersionLocator' type: array maxItems: 3 title: Pronunciation Dictionary Locators description: Pronunciation dictionaries to apply to the text, in order of precedence. Up to 3. model_id: type: string const: eleven_multilingual_v2 title: Model Id description: The model to use for the generation. voice_settings: anyOf: - $ref: '#/components/schemas/TtsVoiceSettings' - type: 'null' description: Overrides for the voice's saved settings, applied to this generation only. additionalProperties: false type: object required: - text - voice - model_id title: ElevenMultilingualV2Request description: Request body for the ElevenLabs Multilingual v2 TTS model. MediaGenerationListResponse: properties: generations: items: $ref: '#/components/schemas/MediaGenerationResponse' type: array title: Generations description: The generations on this page, newest first. Each item has the same shape as the corresponding GET endpoint's response. next_cursor: anyOf: - type: string - type: 'null' title: Next Cursor description: Pass as `cursor` to fetch the next page. `null` when there is no further page. has_more: type: boolean title: Has More description: Whether more generations exist beyond this page. readOnly: true type: object required: - generations - next_cursor - has_more title: MediaGenerationListResponse description: One page of the caller's generations, newest first. example: generations: - content_mime_type: video/mp4 content_url: https://storage.googleapis.com/generations/JWr5N6X9ZTqf8jD2LmQb id: JWr5N6X9ZTqf8jD2LmQb status: completed - id: Kx2mP7Y4WVrg9kE3NnRc status: generating has_more: true next_cursor: MjAyNi0wNy0xN1QxMjowMDowMHxLeDJtUDdZNFdWcmc5a0UzTm5SYw TtsVoiceSettings: properties: stability: anyOf: - type: number maximum: 1.0 minimum: 0.0 - type: 'null' title: Stability description: How consistent the voice stays across generations. Lower values give more expressive, varied speech. similarity_boost: anyOf: - type: number maximum: 1.0 minimum: 0.0 - type: 'null' title: Similarity Boost description: How closely the output adheres to the original voice. style: anyOf: - type: number maximum: 1.0 minimum: 0.0 - type: 'null' title: Style description: How strongly the speaking style is exaggerated. use_speaker_boost: anyOf: - type: boolean - type: 'null' title: Use Speaker Boost description: Whether to boost similarity to the original speaker, at some latency cost. speed: anyOf: - type: number maximum: 1.2 minimum: 0.7 - type: 'null' title: Speed description: The speed of the generated speech, where 1.0 is the voice's natural pace. additionalProperties: false type: object title: TtsVoiceSettings description: Overrides for the voice's saved settings, applied to one generation. ElevenFlashV2_5VoiceSettings: properties: stability: anyOf: - type: number maximum: 1.0 minimum: 0.0 - type: 'null' title: Stability description: How consistent the voice stays across generations. Lower values give more expressive, varied speech. similarity_boost: anyOf: - type: number maximum: 1.0 minimum: 0.0 - type: 'null' title: Similarity Boost description: How closely the output adheres to the original voice. speed: anyOf: - type: number maximum: 1.2 minimum: 0.7 - type: 'null' title: Speed description: The speed of the generated speech, where 1.0 is the voice's natural pace. additionalProperties: false type: object title: ElevenFlashV2_5VoiceSettings description: Overrides for the voice's saved settings, applied to one generation. GPTImage1Request: properties: webhook: anyOf: - $ref: '#/components/schemas/WebhookTarget' - type: 'null' description: Include to send the generation's result to the workspace's configured flows webhooks once it completes or fails. The webhook payload matches the terminal response of the corresponding GET endpoint. examples: - type: all - ids: - Q8mVr2LpXcT4nB6yJdKw type: ids prompt: type: string title: Prompt description: A text description of the image to generate. examples: - A corgi in a tiny lifeguard chair on a sunlit beach at golden hour, photorealistic images: items: $ref: '#/components/schemas/ImageReference' type: array maxItems: 5 title: Images description: Up to 5 reference images to edit or draw from. mask: anyOf: - $ref: '#/components/schemas/ImageReference' - type: 'null' description: An image whose fully transparent areas mark where the first reference image may be edited; requires `images`. quality: type: string enum: - low - medium - high title: Quality description: The quality of the output image. default: medium background: type: string enum: - transparent - opaque - auto title: Background description: The background of the output image. With `auto`, the model picks the background that suits the image. default: auto aspect_ratio: type: string enum: - '1:1' - '3:2' - '2:3' title: Aspect Ratio description: The aspect ratio of the output image. default: '1:1' model_id: type: string const: gpt-image-1 title: Model Id description: The model to use for the generation. additionalProperties: false type: object required: - prompt - model_id title: GPTImage1Request description: Request body for the OpenAI GPT Image 1 model. Gemini3ProImageRequest: properties: webhook: anyOf: - $ref: '#/components/schemas/WebhookTarget' - type: 'null' description: Include to send the generation's result to the workspace's configured flows webhooks once it completes or fails. The webhook payload matches the terminal response of the corresponding GET endpoint. examples: - type: all - ids: - Q8mVr2LpXcT4nB6yJdKw type: ids prompt: type: string title: Prompt description: A text description of the image to generate. examples: - A corgi in a tiny lifeguard chair on a sunlit beach at golden hour, photorealistic model_id: type: string const: gemini-3-pro-image title: Model Id description: The model to use for the generation. images: items: $ref: '#/components/schemas/ImageReference' type: array maxItems: 10 title: Images description: Up to 10 reference images to edit or draw from. aspect_ratio: type: string enum: - auto - '1:1' - '2:3' - '3:2' - '3:4' - '4:3' - '4:5' - '5:4' - '9:16' - '16:9' - '21:9' title: Aspect Ratio description: The aspect ratio of the output image. With `auto`, the model picks an aspect ratio based on the inputs. default: '16:9' resolution: type: string enum: - 1K - 2K - 4K title: Resolution description: The resolution of the output image. default: 1K additionalProperties: false type: object required: - prompt - model_id title: Gemini3ProImageRequest description: Request body for the Google Gemini 3 Pro image model. GPTImage2Request: properties: webhook: anyOf: - $ref: '#/components/schemas/WebhookTarget' - type: 'null' description: Include to send the generation's result to the workspace's configured flows webhooks once it completes or fails. The webhook payload matches the terminal response of the corresponding GET endpoint. examples: - type: all - ids: - Q8mVr2LpXcT4nB6yJdKw type: ids prompt: type: string title: Prompt description: A text description of the image to generate. examples: - A corgi in a tiny lifeguard chair on a sunlit beach at golden hour, photorealistic images: items: $ref: '#/components/schemas/ImageReference' type: array maxItems: 10 title: Images description: Up to 10 reference images to edit or draw from. mask: anyOf: - $ref: '#/components/schemas/ImageReference' - type: 'null' description: An image whose fully transparent areas mark where the first reference image may be edited; requires `images`. quality: type: string enum: - low - medium - high title: Quality description: The quality of the output image. default: medium model_id: type: string const: gpt-image-2 title: Model Id description: The model to use for the generation. aspect_ratio: type: string enum: - auto - '1:1' - '4:5' - '5:4' - '3:4' - '4:3' - '2:3' - '3:2' - '1:2' - '2:1' - '9:16' - '16:9' - '21:9' - '1:3' - '3:1' title: Aspect Ratio description: The aspect ratio of the output image. With `auto`, the model picks an aspect ratio based on the inputs. default: '16:9' resolution: type: string enum: - 1K - 2K - 4K title: Resolution description: The resolution of the output image. default: 1K additionalProperties: false type: object required: - prompt - model_id title: GPTImage2Request description: Request body for the OpenAI GPT Image 2 model. ImageReference: oneOf: - $ref: '#/components/schemas/GenerationReference' - $ref: '#/components/schemas/StaticAssetReference' - $ref: '#/components/schemas/InlineImageReference' discriminator: propertyName: type mapping: asset: '#/components/schemas/StaticAssetReference' generation: '#/components/schemas/GenerationReference' inline_base64: '#/components/schemas/InlineImageReference' BytedanceSeedream5ProRequest: properties: webhook: anyOf: - $ref: '#/components/schemas/WebhookTarget' - type: 'null' description: Include to send the generation's result to the workspace's configured flows webhooks once it completes or fails. The webhook payload matches the terminal response of the corresponding GET endpoint. examples: - type: all - ids: - Q8mVr2LpXcT4nB6yJdKw type: ids prompt: type: string title: Prompt description: A text description of the image to generate. examples: - A corgi in a tiny lifeguard chair on a sunlit beach at golden hour, photorealistic images: items: $ref: '#/components/schemas/ImageReference' type: array maxItems: 10 title: Images description: Up to 10 reference images to edit or draw from. aspect_ratio: type: string enum: - auto - '1:1' - '3:4' - '16:9' - '4:3' - '9:16' title: Aspect Ratio description: The aspect ratio of the output image. With `auto`, the model picks an aspect ratio based on the inputs. default: '16:9' seed: anyOf: - type: integer - type: 'null' title: Seed description: 'A seed for reproducible generation: the same seed and inputs give similar output across generations. Omit for random.' model_id: type: string const: bytedance-seedream-5-pro title: Model Id description: The model to use for the generation. resolution: type: string enum: - 1K - 2K title: Resolution description: The resolution of the output image. default: 2K additionalProperties: false type: object required: - prompt - model_id title: BytedanceSeedream5ProRequest description: 'Request body for the ByteDance Seedream 5.0 Pro image model. ByteDance models are disabled by default and require explicit approval before use. Contact support to request access.' Gemini25FlashImageRequest: properties: webhook: anyOf: - $ref: '#/components/schemas/WebhookTarget' - type: 'null' description: Include to send the generation's result to the workspace's configured flows webhooks once it completes or fails. The webhook payload matches the terminal response of the corresponding GET endpoint. examples: - type: all - ids: - Q8mVr2LpXcT4nB6yJdKw type: ids prompt: type: string title: Prompt description: A text description of the image to generate. examples: - A corgi in a tiny lifeguard chair on a sunlit beach at golden hour, photorealistic model_id: type: string const: gemini-2.5-flash-image title: Model Id description: The model to use for the generation. images: items: $ref: '#/components/schemas/ImageReference' type: array maxItems: 5 title: Images description: Up to 5 reference images to edit or draw from. aspect_ratio: type: string enum: - auto - '1:1' - '2:3' - '3:2' - '3:4' - '4:3' - '4:5' - '5:4' - '9:16' - '16:9' - '21:9' title: Aspect Ratio description: The aspect ratio of the output image. With `auto`, the model picks an aspect ratio based on the inputs. default: '16:9' additionalProperties: false type: object required: - prompt - model_id title: Gemini25FlashImageRequest description: Request body for the Google Gemini 2.5 Flash image model. BytedanceSeedream5LiteRequest: properties: webhook: anyOf: - $ref: '#/components/schemas/WebhookTarget' - type: 'null' description: Include to send the generation's result to the workspace's configured flows webhooks once it completes or fails. The webhook payload matches the terminal response of the corresponding GET endpoint. examples: - type: all - ids: - Q8mVr2LpXcT4nB6yJdKw type: ids prompt: type: string title: Prompt description: A text description of the image to generate. examples: - A corgi in a tiny lifeguard chair on a sunlit beach at golden hour, photorealistic images: items: $ref: '#/components/schemas/ImageReference' type: array maxItems: 10 title: Images description: Up to 10 reference images to edit or draw from. aspect_ratio: type: string enum: - auto - '1:1' - '3:4' - '16:9' - '4:3' - '9:16' title: Aspect Ratio description: The aspect ratio of the output image. With `auto`, the model picks an aspect ratio based on the inputs. default: '16:9' seed: anyOf: - type: integer - type: 'null' title: Seed description: 'A seed for reproducible generation: the same seed and inputs give similar output across generations. Omit for random.' model_id: type: string const: bytedance-seedream-5-lite title: Model Id description: The model to use for the generation. resolution: type: string enum: - 2K - 3K title: Resolution description: The resolution of the output image. default: 2K additionalProperties: false type: object required: - prompt - model_id title: BytedanceSeedream5LiteRequest description: 'Request body for the ByteDance Seedream 5.0 Lite image model. ByteDance models are disabled by default and require explicit approval before use. Contact support to request access.' GenerationReference: properties: type: type: string const: generation title: Type generation_id: type: string title: Generation Id description: The ID of the generation whose output to use, as returned when the generation was created. examples: - JWr5N6X9ZTqf8jD2LmQb additionalProperties: false type: object required: - type - generation_id title: GenerationReference description: The output of a prior generation on this API. CreatifyAuroraRequest: properties: webhook: anyOf: - $ref: '#/components/schemas/WebhookTarget' - type: 'null' description: Include to send the generation's result to the workspace's configured flows webhooks once it completes or fails. The webhook payload matches the terminal response of the corresponding GET endpoint. examples: - type: all - ids: - Q8mVr2LpXcT4nB6yJdKw type: ids model_id: type: string const: creatify-aurora title: Model Id description: The model to use for the generation. image: $ref: '#/components/schemas/ImageReference' description: The image of the character to animate. audio: $ref: '#/components/schemas/AudioReference' description: The speech audio to drive the character's lip movements. resolution: type: string enum: - 480p - 720p title: Resolution description: The resolution of the output video. default: 720p guidance_scale: anyOf: - type: number maximum: 5.0 minimum: 0.0 - type: 'null' title: Guidance Scale description: How strongly the generation adheres to the input image. Omit to use the model's default. audio_guidance_scale: anyOf: - type: number maximum: 5.0 minimum: 0.0 - type: 'null' title: Audio Guidance Scale description: How strongly the lip movements adhere to the audio. Omit to use the model's default. additionalProperties: false type: object required: - model_id - image - audio title: CreatifyAuroraRequest description: Request body for the Creatify Aurora lipsync video model. Veo3_1FastRequest: properties: webhook: anyOf: - $ref: '#/components/schemas/WebhookTarget' - type: 'null' description: Include to send the generation's result to the workspace's configured flows webhooks once it completes or fails. The webhook payload matches the terminal response of the corresponding GET endpoint. examples: - type: all - ids: - Q8mVr2LpXcT4nB6yJdKw type: ids prompt: type: string title: Prompt description: A text description of the video to generate. examples: - A corgi rides a tiny surfboard across a sunlit wave at golden hour, cinematic negative_prompt: anyOf: - type: string - type: 'null' title: Negative Prompt description: A text description of what the video should avoid. seed: anyOf: - type: integer - type: 'null' title: Seed description: 'A seed for reproducible generation: the same seed and inputs give similar output across generations. Omit for random.' enhance_prompt: type: boolean title: Enhance Prompt description: Whether the model may rewrite the prompt to improve results. default: true duration_secs: type: integer enum: - 4 - 6 - 8 title: Duration Secs description: The duration of the output video in seconds. default: 8 aspect_ratio: type: string enum: - '16:9' - '9:16' title: Aspect Ratio description: The aspect ratio of the output video. default: '16:9' resolution: type: string enum: - 720p - 1080p - 4K title: Resolution description: The resolution of the output video. default: 720p generate_audio: type: boolean title: Generate Audio description: Whether to generate audio with the video. default: true start_frame: anyOf: - $ref: '#/components/schemas/ImageReference' - type: 'null' description: The image to use as the video's first frame. end_frame: anyOf: - $ref: '#/components/schemas/ImageReference' - type: 'null' description: The image to use as the video's last frame. images: items: $ref: '#/components/schemas/VeoImageReference' type: array maxItems: 3 title: Images description: Up to 3 reference images to draw subjects or style from. Cannot be combined with `start_frame`/`end_frame`, and requires the 8-second duration. model_id: type: string const: veo-3.1-fast-generate-001 title: Model Id description: The model to use for the generation. additionalProperties: false type: object required: - prompt - model_id title: Veo3_1FastRequest description: Request body for the Google Veo 3.1 Fast video model. VideoReference: oneOf: - $ref: '#/components/schemas/GenerationReference' - $ref: '#/components/schemas/StaticAssetReference' - $ref: '#/components/schemas/InlineVideoReference' discriminator: propertyName: type mapping: asset: '#/components/schemas/StaticAssetReference' generation: '#/components/schemas/GenerationReference' inline_base64: '#/components/schemas/InlineVideoReference' BytedanceSeedance2Request: properties: webhook: anyOf: - $ref: '#/components/schemas/WebhookTarget' - type: 'null' description: Include to send the generation's result to the workspace's configured flows webhooks once it completes or fails. The webhook payload matches the terminal response of the corresponding GET endpoint. examples: - type: all - ids: - Q8mVr2LpXcT4nB6yJdKw type: ids prompt: type: string title: Prompt description: A text description of the video to generate. examples: - A corgi rides a tiny surfboard across a sunlit wave at golden hour, cinematic aspect_ratio: type: string enum: - auto - '21:9' - '16:9' - '4:3' - '1:1' - '3:4' - '9:16' title: Aspect Ratio description: The aspect ratio of the output video. With `auto`, the model picks an aspect ratio based on the inputs. default: '16:9' duration_secs: type: integer maximum: 15.0 minimum: 4.0 title: Duration Secs description: The duration of the output video in seconds. default: 5 seed: anyOf: - type: integer - type: 'null' title: Seed description: 'A seed for reproducible generation: the same seed and inputs give similar output across generations. Omit for random.' generate_audio: type: boolean title: Generate Audio description: Whether to generate audio with the video. default: true start_frame: anyOf: - $ref: '#/components/schemas/ImageReference' - type: 'null' description: The image to use as the video's first frame. end_frame: anyOf: - $ref: '#/components/schemas/ImageReference' - type: 'null' description: The image to use as the video's last frame. images: items: $ref: '#/components/schemas/ImageReference' type: array maxItems: 9 title: Images description: Up to 9 reference images to draw subjects from. Cannot be combined with `start_frame`/`end_frame`. videos: items: $ref: '#/components/schemas/VideoReference' type: array maxItems: 3 title: Videos description: Up to 3 reference videos to draw subjects or motion from. Cannot be combined with `start_frame`/`end_frame`. audios: items: $ref: '#/components/schemas/AudioReference' type: array maxItems: 3 title: Audios description: Up to 3 reference audios, e.g. for lipsync. Requires at least one of `images` or `videos`, and cannot be combined with `start_frame`/`end_frame`. model_id: type: string const: bytedance-seedance-v2 title: Model Id description: The model to use for the generation. resolution: type: string enum: - 480p - 720p - 1080p - 4k title: Resolution description: The resolution of the output video. default: 720p additionalProperties: false type: object required: - prompt - model_id title: BytedanceSeedance2Request description: 'Request body for the ByteDance Seedance 2.0 video model. ByteDance models are disabled by default and require explicit approval before use. Contact support to request access.' BytedanceSeedance2FastRequest: properties: webhook: anyOf: - $ref: '#/components/schemas/WebhookTarget' - type: 'null' description: Include to send the generation's result to the workspace's configured flows webhooks once it completes or fails. The webhook payload matches the terminal response of the corresponding GET endpoint. examples: - type: all - ids: - Q8mVr2LpXcT4nB6yJdKw type: ids prompt: type: string title: Prompt description: A text description of the video to generate. examples: - A corgi rides a tiny surfboard across a sunlit wave at golden hour, cinematic aspect_ratio: type: string enum: - auto - '21:9' - '16:9' - '4:3' - '1:1' - '3:4' - '9:16' title: Aspect Ratio description: The aspect ratio of the output video. With `auto`, the model picks an aspect ratio based on the inputs. default: '16:9' duration_secs: type: integer maximum: 15.0 minimum: 4.0 title: Duration Secs description: The duration of the output video in seconds. default: 5 seed: anyOf: - type: integer - type: 'null' title: Seed description: 'A seed for reproducible generation: the same seed and inputs give similar output across generations. Omit for random.' generate_audio: type: boolean title: Generate Audio description: Whether to generate audio with the video. default: true start_frame: anyOf: - $ref: '#/components/schemas/ImageReference' - type: 'null' description: The image to use as the video's first frame. end_frame: anyOf: - $ref: '#/components/schemas/ImageReference' - type: 'null' description: The image to use as the video's last frame. images: items: $ref: '#/components/schemas/ImageReference' type: array maxItems: 9 title: Images description: Up to 9 reference images to draw subjects from. Cannot be combined with `start_frame`/`end_frame`. videos: items: $ref: '#/components/schemas/VideoReference' type: array maxItems: 3 title: Videos description: Up to 3 reference videos to draw subjects or motion from. Cannot be combined with `start_frame`/`end_frame`. audios: items: $ref: '#/components/schemas/AudioReference' type: array maxItems: 3 title: Audios description: Up to 3 reference audios, e.g. for lipsync. Requires at least one of `images` or `videos`, and cannot be combined with `start_frame`/`end_frame`. model_id: type: string const: bytedance-seedance-v2-fast title: Model Id description: The model to use for the generation. resolution: type: string enum: - 480p - 720p title: Resolution description: The resolution of the output video. default: 720p additionalProperties: false type: object required: - prompt - model_id title: BytedanceSeedance2FastRequest description: 'Request body for the ByteDance Seedance 2.0 Fast video model. ByteDance models are disabled by default and require explicit approval before use. Contact support to request access.' MediaGenerationInProgressResponse: properties: id: type: string title: Id description: The unique identifier of the generation. examples: - JWr5N6X9ZTqf8jD2LmQb status: type: string enum: - pending - generating title: Status description: The lifecycle status of the generation. It ends at `completed` or `failed`. examples: - generating type: object required: - id - status title: MediaGenerationInProgressResponse description: A media generation that has not finished yet. example: id: JWr5N6X9ZTqf8jD2LmQb status: generating BytedanceSeedance2MiniRequest: properties: webhook: anyOf: - $ref: '#/components/schemas/WebhookTarget' - type: 'null' description: Include to send the generation's result to the workspace's configured flows webhooks once it completes or fails. The webhook payload matches the terminal response of the corresponding GET endpoint. examples: - type: all - ids: - Q8mVr2LpXcT4nB6yJdKw type: ids prompt: type: string title: Prompt description: A text description of the video to generate. examples: - A corgi rides a tiny surfboard across a sunlit wave at golden hour, cinematic aspect_ratio: type: string enum: - auto - '21:9' - '16:9' - '4:3' - '1:1' - '3:4' - '9:16' title: Aspect Ratio description: The aspect ratio of the output video. With `auto`, the model picks an aspect ratio based on the inputs. default: '16:9' duration_secs: type: integer maximum: 15.0 minimum: 4.0 title: Duration Secs description: The duration of the output video in seconds. default: 5 seed: anyOf: - type: integer - type: 'null' title: Seed description: 'A seed for reproducible generation: the same seed and inputs give similar output across generations. Omit for random.' generate_audio: type: boolean title: Generate Audio description: Whether to generate audio with the video. default: true start_frame: anyOf: - $ref: '#/components/schemas/ImageReference' - type: 'null' description: The image to use as the video's first frame. end_frame: anyOf: - $ref: '#/components/schemas/ImageReference' - type: 'null' description: The image to use as the video's last frame. images: items: $ref: '#/components/schemas/ImageReference' type: array maxItems: 9 title: Images description: Up to 9 reference images to draw subjects from. Cannot be combined with `start_frame`/`end_frame`. videos: items: $ref: '#/components/schemas/VideoReference' type: array maxItems: 3 title: Videos description: Up to 3 reference videos to draw subjects or motion from. Cannot be combined with `start_frame`/`end_frame`. audios: items: $ref: '#/components/schemas/AudioReference' type: array maxItems: 3 title: Audios description: Up to 3 reference audios, e.g. for lipsync. Requires at least one of `images` or `videos`, and cannot be combined with `start_frame`/`end_frame`. model_id: type: string const: bytedance-seedance-v2-mini title: Model Id description: The model to use for the generation. resolution: type: string enum: - 480p - 720p title: Resolution description: The resolution of the output video. default: 720p additionalProperties: false type: object required: - prompt - model_id title: BytedanceSeedance2MiniRequest description: 'Request body for the ByteDance Seedance 2.0 Mini video model. ByteDance models are disabled by default and require explicit approval before use. Contact support to request access.' TextToSpeechGenerationRequest: oneOf: - $ref: '#/components/schemas/ElevenFlashV2_5Request' - $ref: '#/components/schemas/ElevenMultilingualV2Request' - $ref: '#/components/schemas/ElevenV3Request' discriminator: propertyName: model_id mapping: eleven_flash_v2_5: '#/components/schemas/ElevenFlashV2_5Request' eleven_multilingual_v2: '#/components/schemas/ElevenMultilingualV2Request' eleven_v3: '#/components/schemas/ElevenV3Request' ElevenV3VoiceSettings: properties: stability: anyOf: - type: number maximum: 1.0 minimum: 0.0 - type: 'null' title: Stability description: How consistent the voice stays across generations. Lower values give more expressive, varied speech. additionalProperties: false type: object title: ElevenV3VoiceSettings description: Overrides for the voice's saved settings, applied to one generation. PronunciationDictionaryVersionLocator: properties: pronunciation_dictionary_id: type: string title: Pronunciation Dictionary Id description: The ID of a pronunciation dictionary created via `POST /v1/pronunciation-dictionaries/add-from-file` or `POST /v1/pronunciation-dictionaries/add-from-rules`. examples: - 5xM3yVvZQKV0EfqQpLrJ version_id: anyOf: - type: string - type: 'null' title: Version Id description: The version of the dictionary to use. Omit to use the latest version. additionalProperties: false type: object required: - pronunciation_dictionary_id title: PronunciationDictionaryVersionLocator description: A pronunciation dictionary to apply during speech synthesis.