All tasks / Models
OmniHuman 2.0
ByteDance's audio-driven human video model: animates a single photo into a talking, gesturing video of up to 5 minutes.
- ByteDance (BytePlus)
- Closed
- Released 15 Oct 2026
Where it ranks
- –Avatars & dubbingModels · Cloud · no result on this task’s benchmarks yet
Facts
- Vendor
- ByteDance (BytePlus)
- Family
- OmniHuman
- Released
- 15 Oct 2026
- Weights
- Closed: API and apps only
- API price
- $0.07 per second of video (BytePlus launch price ($0.07 per second, 40% cut) as reported by Webrazzi; BytePlus page not read directly; fal.ai hosts bytedance/omnihuman/v2 at $0.105/s)
- Last verified
- 18 Oct 2026
Price from webrazzi.com, 18 Oct 2026.
Benchmark results
No public benchmark results recorded yet.
Where you can use it
No tracked tool lists this model yet.
Earlier versions
- OmniHuman 1.5 · —
- OmniHuman-1 · Feb 2025