Seedance 2.0 Fast 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
izakaya-across-the-smoke Written from nothing at `duration_seconds` `5`, `720p`, `16:9`, with `generate_audio` left on. The brief hands the render one continuous obscuring element — oil smoke that keeps softening and revealing two faces — so the interest lies in what it does across five seconds rather than in any single frame. The griddle noise comes back in the same file and is cut against the picture, not laid under it.
- 720p
- 16:9
- audio
- Output5s
bus-window-selfie The clip shown on this page, request and all: five seconds at 720p in 9:16, audio on. The prompt asks for phone-camera realism rather than cinema, which is what sells it as a selfie.
- 720p
- 9:16
- audio
- Output5s
tunnel-retreat One unbroken retreating track at walking pace, with the strip lights streaking overhead to prove the camera really is moving rather than the scene sliding. Audio is off on purpose: this is a plate meant to sit under a track, and the tunnel would otherwise arrive with its own reverb.
- 720p
- 16:9
- 5s
- Output5s
high-key-tennis The second clip on this page, request and all. The exposure is written into the prompt rather than fixed afterwards: asking for blown highlights and heat shimmer is what makes the court read as hot.
- 720p
- 16:9
- audio
This example starts at $0.045 per output second. The Playground updates the estimate when you change the settings.