For a Turbo reference take, combine up to 9 images, 2 video clips with a 15-second total and 3 audio clips, directing each by its Image, Video or Audio number. A Turbo take can last any whole number from 2 to 15 seconds, with 5 selected by default and 24 fps output.
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
gala-staircase-arm Two portraits, each referred to by position, and one slow beat on a staircase. Both faces were kept; the model also added a whispered line that was not in the prompt.
- 720p
- 16:9
- 5s
- Output5s
studio-spin-reference One portrait in 9:16 and a short move list. "Keep her braids and outfit from Image 1" holds the look; the clip follows the spin and body roll.
- 720p
- 9:16
- 5s
This example starts at $0.015 per output second. The Playground updates the estimate when you change the settings.