> ## Documentation Index > Fetch the complete documentation index at: https://docs.ttapi.io/llms.txt > Use this file to discover all available pages before exploring further. > ## Agent Instructions > Send API requests to https://api.ttapi.io with the TT-API-KEY header. Midjourney account hosting uses https://hold.ttapi.io. Claude Code uses https://cc.ttapi.io. > Most generation endpoints are asynchronous. The submit response returns a job id. Poll that product's fetch endpoint, or pass a webhook on the submit request. A fetch call does not start a new generation. > 1 USD = 100 quota. Check the pricing page for that product before estimating cost. > This file lists the English docs. Follow every /_llms/ link recursively for the API reference, Chinese, and Russian. Open a page's .md URL for the endpoint schema. # Audio Video - First Frame > Audio video - first frame. Generate video with synchronized audio from single first frame image and text prompt. All 4 models. Submit async task and return id, use query endpoint to get results. This is the **Seedance Video Generation API** audio video - first frame endpoint. Generate video with synchronized audio based on single first frame image and text prompt. All 4 models supported. Submit async task and return id, use query endpoint to get results. **Usage**: Include `text` (prompt), `image_url` (first frame, role=first\_frame), and optional `audio_url` (reference audio, role=reference\_audio) in `content`, set `generate_audio: true`. `ratio` is `adaptive` to automatically match first frame image. ## OpenAPI ````yaml openapi/en/seedance-audio-first-frame.json POST /sd/api/v3/contents/generations/tasks openapi: 3.1.0 info: title: Seedance Video Generation API (Audio Video - First Frame) version: 1.0.0 description: Generate audio video from first frame image. servers: - url: https://api.ttapi.io security: [] paths: /sd/api/v3/contents/generations/tasks: post: description: >- Audio video - first frame. Generate video with synchronized audio from single first frame image and text prompt. All 4 models. Submit async task and return id, use query endpoint to get results. requestBody: required: true content: application/json: schema: $ref: '#/components/schemas/CreateRequest' example: model: doubao-seedance-2-5-260628 content: - type: text text: A girl walking on the beach, breeze blowing her hair - type: image_url image_url: url: https://example.com/first_frame.jpg role: first_frame ratio: adaptive duration: 15 generate_audio: true output_format: mp4 watermark: true responses: '200': description: Task submitted successfully content: application/json: schema: type: object properties: id: type: string description: Task ID example: id: cgt-20261021120000-xxxxx required: - id security: - CustomApiKey: [] components: schemas: CreateRequest: type: object properties: model: type: string enum: - doubao-seedance-2-5-260628 - doubao-seedance-2-0-260128 - doubao-seedance-2-0-fast-260128 - doubao-seedance-2-0-mini-260615 description: Model ID content: type: array items: $ref: '#/components/schemas/ContentItem' description: >- Input content list. Must include image_url (first frame), optional text and audio_url resolution: type: string enum: - 480p - 720p - 1080p default: 720p description: >- Video resolution. Seedance 2.5 options: 480p, 720p, 1080p. Default 720p ratio: type: string enum: - adaptive description: >- Video aspect ratio, only adaptive supported (auto-matches first frame image) duration: type: integer default: -1 description: Video duration (seconds). Range [4, 30] or -1 (smart selection) generate_audio: type: boolean default: true description: >- Whether to generate synchronized audio. true=includes vocals/SFX/BGM, false=silent video output_format: type: string enum: - mp4 - mov default: mp4 description: Output format. Only Seedance 2.5 supported watermark: type: boolean default: false description: Whether to add watermark return_last_frame: type: boolean default: false description: Whether to return last frame image draft: type: boolean default: false description: Whether to enable draft mode. Only Seedance 2.5 supported callback_url: type: string description: Callback URL execution_expires_after: type: integer default: 172800 description: Task timeout threshold (seconds). Range [3600, 259200] priority: type: integer default: 0 description: Execution priority. Range [0, 9] safety_identifier: type: string description: End user identifier, max 64 characters tools: type: array items: type: object properties: type: type: string enum: - web_search description: Tool configuration service_tier: type: string enum: - default default: default description: Service tier required: - model - content ContentItem: type: object description: Input content item oneOf: - type: object properties: type: type: string enum: - text text: type: string description: Text prompt describing the desired video content required: - type - text - type: object properties: type: type: string enum: - image_url image_url: type: object properties: url: type: string description: >- First frame image URL / Base64. Formats: jpeg/png/webp/bmp/tiff/gif/heic/heif，Aspect ratio [0.4, 2.5]，size < 30MB role: type: string enum: - first_frame description: >- First frame identifier. Role is first_frame for first frame scenario, or leave empty required: - type - image_url - type: object properties: type: type: string enum: - audio_url audio_url: type: object properties: url: type: string description: >- Audio URL / Base64 / Asset ID. Format: wav/mp3, duration [2, 30]s, size ≤ 15MB role: type: string enum: - reference_audio description: Fixed as reference_audio required: - type - audio_url - role securitySchemes: CustomApiKey: type: apiKey in: header name: TT-API-KEY description: >- Get your API key from the TTAPI Dashboard. ```` This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.