Create a Seedance 2.0 video (platform format)

Supports text, image, video, and audio inputs for text-to-video, first-frame or first-and-last-frame control, and reference-asset generation.

To use the Volcengine Ark request structure directly, see the native-format create API.

Standard Seedance 2.0 supports 480p/720p/1080p/4k; Seedance 2.0 fast supports only 480p/720p. Select a resolution supported by the actual model.

POST/v1/video/generations

Create an asynchronous video generation task. A successful submission returns a task ID; the video is not returned synchronously by this API.

Supported models include doubao-seedance-2-0-260128 and doubao-seedance-2-0-fast-260128. The models actually available are determined by the model list returned for the current API Key.

Authorization

bearerAuth

AuthorizationBearer <token>

Use Bearer your-api-key in the Authorization Header.

In: header

Request Body

application/json

Seedance 2.0 video generation parameters.

TypeScript Definitions

Use the request body type in TypeScript.

model*string

Seedance 2.0 model ID or the ID of an inference endpoint configured with this model. Supported values include doubao-seedance-2-0-260128 and doubao-seedance-2-0-fast-260128; actual availability depends on the current API Key.

Length1 <= length

content*array<>

Input items. Reference mode accepts up to 9 images, 3 videos, and 3 audio clips. Each video or audio clip must be 2–15 seconds; the total duration of each media type must not exceed 15 seconds. Audio requires at least one image or video. First-frame and first-and-last-frame modes cannot be mixed with omni reference.

Items1 <= items

generate_audio?boolean

Whether to generate audio synchronized with the visuals. When true, the model may generate matching speech, sound effects, and background music from the prompt and visual content. When false, the output video is silent.

ratio?string

Video aspect ratio. Seedance 2.0 and Seedance 2.0 fast use adaptive by default to select an appropriate aspect ratio from the input.

Default"adaptive"

Value in

"16:9"
"4:3"
"1:1"
"3:4"
"9:16"
"21:9"
"adaptive"

duration?|unknown

Generated video duration in seconds. Seedance 2.0 and Seedance 2.0 fast support integers from 4 to 15, or -1 to let the model choose the duration.

resolution?string

Video resolution, default 720p. Standard Seedance 2.0 supports 480p/720p/1080p/4k; Seedance 2.0 fast supports only 480p/720p.

Default"720p"

Value in

"480p"
"720p"
"1080p"
"4k"

watermark?boolean

Whether to add a watermark to the generated video.

seed?integer

Random seed from -1 to 4294967295. Using the same seed may improve reproducibility but does not guarantee identical results.

Range-1 <= value <= 4294967295

return_last_frame?boolean

Whether to return a watermark-free JPEG last frame for generating consecutive videos.

callback_url?string

URL that receives a POST callback when the task status changes. The callback body matches the task retrieval response. If omitted, poll the retrieve API for task status.

Formaturi

safety_identifier?string

Stable unique identifier for the end user, used to help identify users who may violate usage policies. Send a hashed username, user ID, or email address and avoid submitting personal information.

Length1 <= length <= 64

execution_expires_after?integer

Task lifetime in seconds, measured from creation. A task that remains incomplete after this period is terminated and marked expired.

Formatint32

Range3600 <= value <= 259200

Default172800

tools?array<>

Tools the model may call, such as web_search. Tool types and extension parameters depend on the current model and account capabilities.

service_tier?string

Service tier used by the task. Seedance 2.0 and Seedance 2.0 fast use the default online inference service and do not support flex offline inference.

Default"default"

priority?integer

Queue priority within the same inference endpoint, from 0 to 9. Higher values take precedence; equal priorities follow submission order. Running tasks are not interrupted.

Range0 <= value <= 9

Default0

Response Body

`application/json`

curl -X POST "https://example.com/v1/video/generations" \  -H "Content-Type: application/json" \  -d '{    "model": "MODEL_ID",    "content": [      {        "type": "text",        "text": "A little Christmas rabbit is flying"      }    ],    "generate_audio": true,    "ratio": "16:9",    "duration": 11,    "resolution": "1080p",    "watermark": false,    "execution_expires_after": 172800  }'

{
  "id": "cgt-20260330164007-wnc8k",
  "task_id": "cgt-20260330164007-wnc8k",
  "object": "video",
  "model": "MODEL_ID",
  "status": "queued",
  "progress": 0,
  "created_at": 1774860007
}

Official Volcengine Ark documentation for creating video generation tasksReview the upstream protocol definition and the latest field changes for Seedance video generation tasks.

Create a Seedance 2.0 video (platform format)

Authorization

Request Body

Response Body

200application/json

400application/json

401application/json

402application/json

429application/json

500application/json

502application/json

`application/json`

`application/json`

`application/json`

`application/json`

`application/json`

`application/json`

`application/json`