Overview
These endpoints are for teams that already use the Volc-style Seedance task shape. They preserve the task-oriented request and response structure while using TokenLab authentication, billing, model availability, and task polling. See also Seedance 2.0 Video Models and Video Generation.Authentication And Endpoints
- Use
Authorization: Bearer <TOKENLAB_API_KEY>. - Volc AK/SK signing is not accepted in this version. Requests with only AK/SK signing return a Volc-style authentication error.
Versionmay be omitted. If provided, it must be2024-01-01.
| Mode | Request |
|---|---|
| REST create | POST /api/v3/contents/generations/tasks |
| Action create | POST /api/v3?Action=CreateContentsGenerationsTasks&Version=2024-01-01 |
Content Rules
type: "text"is the prompt text.type: "image_url"withoutrole, or withrole: "first_frame", is treated as the first frame.role: "last_frame"must be paired with a first frame.role: "reference_image",reference_video, andreference_audioare used as references.- Do not mix first/last frame inputs with reference media in one request.
Parameter Notes
ratioaccepts16:9,4:3,1:1,3:4,9:16,21:9, oradaptive.durationis the video length in seconds, including model-supported automatic duration values.resolutionaccepts480p,720p,1080p, or4kwhen supported by the selected Seedance model.generate_audiodefaults totrue; set it tofalsefor a silent video.watermark,return_last_frame,seed,priority,execution_expires_after, andsafety_identifierare accepted when valid for the selected model.callback_urlis not supported yet. Poll task status instead.
Image Preparation
Whencontent[] contains image URLs, TokenLab prepares them as reusable materials when required by the selected Seedance model. If preparation is not complete within 60 seconds, the create request returns a retryable material-preparing error instead of submitting an incomplete video task.
Create Response
Example
REST Create
Action Create
Next Step
Use the returnedcgt-... ID with Get Task (Volc Compatible) until the task reaches a terminal status.