Alibaba's Wan 2.6 text-to-video turns a written shot or shot list into 5, 10 or 15 seconds with generated sound, at 720p or 1080p. Choose one of five aspect ratios and a single take or multi-shot edit.
Filtering differs by endpoint: Image to video — Uncensored, Text to video — Uncensored, Reference to video — Filtered.
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
rain-car-climb-over - 720p
- 16:9
- 5s
- Output10s
numbered-shot-list The prompt is a numbered shot list rather than prose: 1 wide, 2 medium, 3 close. This endpoint reads that structure and shoots it in order, which is why each of the three lines names a size and a subject and nothing else. Keep the numbering strict and keep one shot per line — the moment a line describes two events, the boundary between shots stops being yours. `duration_seconds` `10`, `1080p`.
- 1080p
- 16:9
- 10s
- Output5s
harbour-rain-single One action and one slow camera move at 16:9, with the sound written out so the horn and the rain sit under the picture.
- 720p
- 16:9
- 5s
- Output10s
bakery-morning-multi Three numbered shots in a vertical ten-second clip at 1080p, with prompt expansion on so the model can plan the cuts.
- 20251216
- multi
- 1080p
This example starts at $0.09 per output second. The Playground updates the estimate when you change the settings.