> ## Documentation Index > Fetch the complete documentation index at: https://docs.cubeuaeai.com/llms.txt > Use this file to discover all available pages before exploring further. # Seedance 2.0 Fast > Create an asynchronous video generation task. Supports text-to-video, image-to-video, multimodal references, video editing, video extension, and web-search enhancement. ## OpenAPI ````yaml en/api-reference/model-api/bytedance/openapi/seedance-2-0-fast/openapi.yaml POST /v1/video/generations openapi: 3.1.0 info: title: Seedance 2.0 Fast description: >- Call the ByteDance Seedance 2.0 Fast video generation model. Supports text-to-video, image-to-video, multimodal references, video editing, video extension, and web-search enhancement version: 1.0.0 servers: - url: https://ai.cubeuaeai.com security: - bearerAuth: [] paths: /v1/video/generations: post: summary: Create a video generation task description: > Create an asynchronous video generation task. Multiple input modes are supported: - Text-to-video - Image-to-video (first frame / first and last frame) - Multimodal reference (image + video + audio combinations) - Edit video - Extend video - Web-search enhancement After submitting, poll `GET /v1/video/generations/{id}` until `status` is `succeeded`. operationId: createSeedanceFastZh requestBody: required: true content: application/json: schema: type: object required: - model - content properties: model: type: string enum: - seedance-fast description: model ID example: seedance-fast content: type: array description: > Input content array. Supports combinations of text, image, video, and audio: - Text - Text (optional) + image - Text (optional) + video - Text (optional) + image + audio - Text (optional) + image + video - Text (optional) + video + audio - Text (optional) + image + video + audio items: type: object properties: type: type: string enum: - text - image_url - video_url - audio_url description: > Content types: - `text` — text prompt - `image_url` — image input (first frame / last frame / reference image) - `video_url` — video input (reference video) - `audio_url` — audio input (reference audio) text: type: string description: >- Text prompt describing the desired video. Recommended: up to 500 Chinese characters or 1000 English words. image_url: type: object description: Image object. properties: url: type: string description: > Image URL, Base64 encoding, or asset ID (`asset://`). Supported formats: jpeg, png, webp, bmp, tiff, gif. Each image ≤ 30 MB. video_url: type: object description: Video object. properties: url: type: string description: > Video URL or asset ID (`asset://`). Supported formats: mp4, mov. Each file ≤ 50 MB, duration 2–15 seconds. audio_url: type: object description: >- Audio object. Cannot be used alone; at least one reference video or image is required. properties: url: type: string description: > Audio URL, Base64 encoding, or asset ID (`asset://`). Supported formats: wav, mp3. Each file ≤ 15 MB, duration 2–15 seconds. role: type: string enum: - first_frame - last_frame - reference_image - reference_video - reference_audio description: > Role of the content item: - `first_frame` — first-frame image (image-to-video) - `last_frame` — last-frame image (first-and-last-frame mode) - `reference_image` — reference image (multimodal reference, 1–9 images) - `reference_video` — reference video (multimodal reference, up to 3) - `reference_audio` — reference audio (multimodal reference, up to 3) example: - type: text text: A cat playing the piano in a sunlit room - type: image_url image_url: url: https://example.com/reference.jpg role: reference_image generate_audio: type: boolean default: true description: > Controls whether the generated video includes synchronized audio. - `true` — automatically generate speech, sound effects, and background music - `false` — silent video resolution: type: string enum: - 480p - 720p - 1080p default: 720p description: Output video resolution. ratio: type: string enum: - '16:9' - '4:3' - '1:1' - '3:4' - '9:16' - '21:9' - adaptive default: adaptive description: > Output aspect ratio. `adaptive` automatically chooses the best ratio from the input. duration: type: integer minimum: 4 maximum: 15 default: 5 description: | Video duration in seconds. Integer, 4–15. tools: type: array description: >- Tools the model can call. Currently supports web search (text-to-video only). items: type: object properties: type: type: string enum: - web_search description: Tool type. `web_search` enables web search. watermark: type: boolean default: false description: Whether to add a watermark. responses: '200': description: Video generation task created content: application/json: schema: type: object properties: id: type: string description: Task ID example: cgt-20260312231129-7db6s task_id: type: string description: Task ID (same as id) example: cgt-20260312231129-7db6s object: type: string example: video model: type: string example: seedance-fast status: type: string description: Initially empty example: '' progress: type: integer example: 0 created_at: type: integer description: Unix timestamp example: 1773328294 '400': description: Invalid request parameters content: application/json: schema: $ref: '#/components/schemas/Error' '401': description: Unauthorized content: application/json: schema: $ref: '#/components/schemas/Error' components: schemas: Error: type: object properties: error: type: object properties: code: type: string message: type: string securitySchemes: bearerAuth: type: http scheme: bearer ````