Seedance 2 Fast | BeatAPI API Documentation

curl -X POST https://api.beatapi.io/v1/videos/tasks \
     -H "Authorization: Bearer <token>" \
     -H "Content-Type: application/json" \
     -d '{
  "model": "seedance-2-fast",
  "prompt": "A fast handheld tracking shot through a crowded neon night market.",
  "duration": 5,
  "aspect_ratio": "16:9",
  "resolution": "720p",
  "generate_audio": true
}'

{
  "data": {
    "capability_id": "seedance-2-fast",
    "capability_version": null,
    "completed_at": null,
    "created_at": 1782210000,
    "error_code": null,
    "error_message": null,
    "id": "task_8K2qA",
    "media_type": "video",
    "model": "seedance-2-fast",
    "object": "task",
    "output": null,
    "request_id": "req_abc123",
    "stage": "queued",
    "status": "queued",
    "task_kind": "video",
    "updated_at": 1782210000,
    "usage": {
      "billable_duration_seconds": 5,
      "credits_charged": 0.7,
      "credits_refunded": 0,
      "credits_reserved": 0.7,
      "credits_settled": 0
    }
  }
}

Generate 4–15 second 480p or 720p videos through the official faster Seedance 2.0 route, with optional generated audio.

Supported modes

Mode	Required input	Rules
Text to video	`model`, `prompt`	Omit all media arrays.
First frame	`model`, `prompt`, `images`	Provide one image URL; provide two for first and last frames.
Multimodal references	`model`, `prompt`, one `reference_*` array	Audio references also require a reference image or video.

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.

Generate 4–15 second 480p or 720p videos through the official faster Seedance 2.0 route, with optional generated audio. ### Supported modes | Mode | Required input | Rules | | --- | --- | --- | | Text to video | `model`, `prompt` | Omit all media arrays. | | First frame | `model`, `prompt`, `images` | Provide one image URL; provide two for first and last frames. | | Multimodal references | `model`, `prompt`, one `reference_*` array | Audio references also require a reference image or video. | **Async flow:** Create the task, save `data.id`, then [poll the Task](/quick-guide#get-task-status) 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](/quick-guide#errors-and-retry-policy). **Using a local file?** [upload a local input](/quick-guide#upload-an-input-file) first and pass the returned `data.url`.

身份验证

AuthorizationBearer

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

请求

This endpoint expects an object.

model"seedance-2-fast"必需

Must be seedance-2-fast.

promptstring必需1-5000 characters

Video generation instructions.

imageslist of strings可选

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

reference_imageslist of strings可选

Public HTTPS image references for multimodal reference generation.

reference_videoslist of strings可选

Public HTTPS video references for multimodal reference generation.

reference_audioslist of strings可选

Public HTTPS audio references. Audio also requires at least one reference image or video.

durationinteger可选4-15默认为 5

Requested output duration in seconds.

aspect_ratioenum可选默认为 adaptive

Output video aspect ratio.

resolutionenum可选默认为 720p

Output resolution tier.

generate_audioboolean可选默认为 true

Generate synchronized audio with the video.

响应

Video generation task accepted

错误

400

Bad Request Error

401

Unauthorized Error

402

Payment Required Error

409

Conflict Error

429

Too Many Requests Error

Generate 4–15 second 480p or 720p videos through the official faster Seedance 2.0 route, with optional generated audio.

Supported modes

Mode	Required input	Rules
Text to video	`model`, `prompt`	Omit all media arrays.
First frame	`model`, `prompt`, `images`	Provide one image URL; provide two for first and last frames.
Multimodal references	`model`, `prompt`, one `reference_*` array	Audio references also require a reference image or video.

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

Supported modes

身份验证

请求头

请求

响应

错误

Supported modes