Create video task
Create an asynchronous text-to-video or image-to-video task. Use JSON when there are no reference images and multipart/form-data when reference images are present.
Authorizations
Bearer authentication header of the form Bearer <token>, where <token> is your auth token.
Headers
Client-generated idempotency key for safe retries of the same logical video task creation request.
Body
- Option 1
- Option 2
Video model ID.
"seedance-2.0-mini"
Video request type, such as text-to-video or image-to-video.
text-to-video, image-to-video "text-to-video"
Text instruction for the video.
"Waves crashing on rocks, cinematic slow motion"
Requested duration in seconds. Must be listed in the selected model's capabilities.supported_seconds.
8
Compatibility alias for duration.
8
Requested output resolution. Must be listed in the selected model's capabilities.supported_sizes when provided.
"720p"
Compatibility alias for resolution. Legacy models can expose exact sizes such as 1280x720.
"1280x720"
Client-generated request ID for tracing and retry correlation.
"video-demo-001"
Response
Queued video task
Video task ID.
"video_task_id"
Video task status.
queued, in_progress, completed, failed, timeout "queued"
Completed output URLs. Empty or omitted until the task is completed.
Task error details for failed or timed-out tasks.
