FLUX 3 text-to-video writes picture and synchronized sound from a prompt, in clips of 5 to 20 seconds at 720p or 1080p, with a cheap draft tier for previews.
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.
- Output6s
night-train-late A 1080p sleeper-car scene at 16:9 with one quoted line. The line in the clip matches the prompt, the camera pushes in slowly, and the city beyond the window reads more like lights seen from above than lights streaking past.
- 1080p
- 16:9
- audio
- Output6s
gym-hand-wraps A 720p boxing-gym scene at 21:9 with a spoken line and tape-and-rope sounds. The hand wrapping is a little vague, and the grey shirt came back a little different from the prompt.
- 720p
- 21:9
- audio
- Output8s
neon-diner-booth A draft-tier vertical clip at 9:16. The booth is empty for the first second or so before the camera slides across to the two women; detail is softer than standard, and the hair-tuck reads more like a hand resting at the cheek.
- draft
- 9:16
- audio
This example starts at $0.06 per output second. The Playground updates the estimate when you change the settings.