ByteDance's Seedance 2.5 text-to-video builds the whole frame from a written prompt, with sound in the same pass. Clips run 4 to 30 seconds at 480p, 720p or 1080p, in six aspect ratios, and come back as MP4 or MOV.
Workbench
These examples were written for this endpoint. Replace the prompt and sample media URLs with your own accessible inputs, then check the current quote and model availability before submitting.
- Output4s
night-train-press - 720p
- 16:9
- audio
- Output5s
laundromat-3am The second clip on this page, request and all. Same five seconds, 720p and 16:9 as the shot above it, but the prompt asks for monochrome 16mm and a loose handheld drift — a reminder that stock and camera behaviour are prompt decisions here, not settings.
- 720p
- 16:9
- audio
- Output5s
dawn-macro-breath The smallest shot this family can be asked for: a 100mm macro on a face and shoulder, camera locked, and only two events in five seconds — a breath out and the eyes opening. A bead of water runs from the hairline down the jaw, which is the detail that tells you whether the render is holding at this distance.
- 720p
- 16:9
- audio
- Output5s
jazz-bar-whisper The clip shown on this page, request and all: five seconds at 720p, 16:9, audio on. The wording deliberately carries the closeness through a whisper and touching foreheads, which passes where kissing wording does not.
- 720p
- 16:9
- audio
This example starts at $0.123 per output second. The Playground updates the estimate when you change the settings.