Seedance 1.5 Pro text-to-video from ByteDance builds a whole shot from a written prompt and renders the soundtrack in the same pass. Clips run 4 to 12 seconds at 480p, 720p or 1080p, in six aspect ratios, with an optional camera lock.
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
seance-candle-bare-feet Written from nothing with the camera locked and `generate_audio` on, at `duration_seconds` `5` and `resolution` `720p` in `3:4`. Almost the whole brief is about what does not move: a figure settled and still, candle flames leaning and recovering, their shadows travelling. A locked text-to-video call is worth running before you commission a still, because it tells you whether a scene reads at all without camera movement doing the work.
- 720p
- 3:4
- audio
- Output5s
locked-hotel-wide The clip shown on this page, request and all: camera_fixed true, five seconds at 720p, 16:9, audio on. Every bit of motion in it belongs to the subject or the fabric around her.
- 720p
- 16:9
- fixed
- Output5s
candlelit-vanity The other half of the pair, request and all. Same endpoint, same five seconds at 720p and 16:9 as the locked shot above, but camera_fixed is off and the prompt asks for a very slow dolly in. Run the two side by side and the switch is the only thing that differs.
- 720p
- 16:9
- audio
- Output5s
rehearsal-orbit The third position in the camera_fixed comparison above it: not a locked frame, not a slow dolly, but a full 180-degree orbit from profile round to front while she follows the lens with her eyes. Put the three side by side and the field is the only thing that changed.
- 720p
- 16:9
- audio
This example starts at $0.011 per output second. The Playground updates the estimate when you change the settings.