ナビゲーションにスキップ

Seedance 2

Generate 4–15 second videos from text, first/last frames, or multimodal references, with optional generated audio.

Supported modes

ModeRequired inputRules
Text to videomodel, promptOmit all media arrays.
First framemodel, prompt, imagesProvide one image URL; provide two for first and last frames.
Multimodal referencesmodel, prompt, one reference_* arrayAudio references also require a reference image or video.

Reference videos: each second of reference_videos is billed at the same per-second rate as the output, for as long as the references run (15 seconds at most in total). Their length is read when the task is created and that is what is held; when it cannot be read, the 15-second maximum is held and the unused part is refunded when the task finishes. A request with a reference video is never billed below 1.5 times the price of the same output without one, which is what applies when the reference is much shorter than the output.

Async flow: Create the task, save data.id, then poll the Task with GET /v1/tasks/{task_id}. On succeeded, read data.output.media. On failed, read data.error_code and data.error_message, then follow the error and retry policy.

Using a local file? upload a local input first and pass the returned data.url.

認証

AuthorizationBearer

Send your API key as Authorization: Bearer <BEATAPI_API_KEY>.

ヘッダー

Idempotency-Keystringオプション<=255 characters

リクエスト

This endpoint expects an object.
model"seedance-2"必須

Must be seedance-2.

promptstring必須1-5000 characters
Video generation instructions.
imageslist of stringsオプション

One first-frame image or first- and last-frame images as public HTTPS URLs.

reference_imageslist of stringsオプション
Public HTTPS image references for multimodal reference generation.
reference_videoslist of stringsオプション
Public HTTPS video references for multimodal reference generation.
reference_audioslist of stringsオプション
Public HTTPS audio references. Audio also requires at least one reference image or video.
durationintegerオプション4-15デフォルト値 5
Requested output duration in seconds.
aspect_ratioenumオプションデフォルト値 adaptive
Output video aspect ratio.
resolutionenumオプションデフォルト値 720p
Output resolution tier. 4k and 4K are equivalent. 1080p is not supported with reference images.
許可された値:
generate_audiobooleanオプションデフォルト値 true
Generate synchronized audio with the video.

レスポンス

Video generation task accepted

エラー

400
Bad Request Error
401
Unauthorized Error
402
Payment Required Error
403
Forbidden Error
409
Conflict Error
429
Too Many Requests Error
500
Internal Server Error
503
Service Unavailable Error