seedance-2-0-fast
ByteDance Seed’s low-latency joint audio-video model supports four-modal references, synchronized 4–15 second clips, and multi-shot control for rapid iteration, batch video creation, and creative previews.
Authorizations
Bearer authentication header of the form Bearer <token>, where <token> is your auth token.
Body
seedance-2-0-fast Required for text-to-video; optional when visual references are provided.
5000Optional image-to-video start frame; cannot be mixed with reference media.
Optional end frame; requires first_frame_image.
Up to 9 reference image URLs; cannot be combined with first or last frame.
9Up to 3 reference video URLs; cannot be combined with first or last frame.
3Up to 3 reference audio URLs; requires at least one reference image or video and cannot be combined with first/last frame.
3Must be one of: 480P, 720P. Defaults to 720P.
480P, 720P 4-15 seconds; -1 means intelligent duration. Defaults to 5. Value is in s.
-1, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15 Fast maps explicit ratios to the correct upstream ratio/aspect_ratio field for each mode. Defaults to adaptive.
16x9, 1x1, 21x9, 3x4, 4x3, 9x16, adaptive Enable or disable synchronized generated audio; unset uses the provider default.
Response
Business response. code=0 means the task was accepted; validation failures can return HTTP 200 with code=400.