Seedance 2.0 Mini text-to-video from ByteDance builds the whole frame from a written prompt, with sound in the same pass. Clips run 4 to 15 seconds at 480p or 720p, in seven aspect ratios including adaptive, or let the model pick the length.
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.
- Output5s
familiar-window-two-woke Written from nothing at `duration_seconds` `5`, `720p`, `16:9`, with `generate_audio` on. Two near-static figures and one moving animal is a good check on a small tier: the cat has to cross and settle while the people stay convincingly still, which is harder than it sounds when everything in frame is free to drift. Sound is rendered against the picture in the same pass rather than added afterwards.
- 720p
- 16:9
- audio
- Output5s
studio-morning The clip shown on this page, request and all: five seconds at 720p, 16:9, audio on. Ordinary coverage, which is exactly what this tier is for.
- 720p
- 16:9
- audio
- Output5s
rain-shopfront-laugh The two clips around it are a bright room and a hand-painted anime frame; this one is heavy rain at night on a telephoto, with magenta and green sign light coming through the downpour. Water is the load here — sheeting off the awning, spray from a passing bus — and the smallest tier carries it at five seconds.
- 720p
- 16:9
- audio
- Output5s
snowy-onsen-anime The second clip on this page, request and all. Naming the technique — cel shading, crisp linework, flat painted shadows — is what keeps it from drifting back toward photoreal; the smallest tier renders illustration as readily as live action.
- 720p
- 16:9
- audio
This example starts at $0.025 per output second. The Playground updates the estimate when you change the settings.