ByteDance's OmniHuman 1.5 is the 1.5 model in its portrait-animation series, combining speech or singing with optional gesture and camera direction at 720p or 1080p.
From $0.144/s
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
An invitation in a sleeper-train compartment A 1024×1536 train-compartment portrait, 6.35-second invitation, and gesture prompt at 1080p returned 1248×1664, 25 fps, and 6.44 seconds. She raised one hand palm up, nodded, and smiled while speaking; framing changed to 3:4, and the audio counted as 7 billable seconds.
- 1080p
This example starts at $0.144 per output second. The Playground updates the estimate when you change the settings.
