About
About OmniHuman 2
OmniHuman 2 is an independent studio for turning one photo and one audio track into a video of that person talking or singing.
What this site does
You upload a single picture of one person and one audio track, choose a 5, 10 or 15 second clip and generate a video in the browser. The picture fixes who appears and how the shot is framed; the audio is the performance. Both inputs are required.
How it fits your work
The studio is built for short, spoken or sung clips: an explainer line, a chorus, a product read, a podcast intro. You keep the same photo and re-run it with a new audio track whenever the script changes, so a recurring presenter does not need a new shoot each time.
Who it is for
Creators, teachers, marketers and small teams who already have a picture and a recording and want them combined without editing software. Paid generation needs an account and spends credits, and the cost is shown before you start.
Your material, your responsibility
Only upload photos, voices and likenesses you have the right to use. If a person other than you appears in the picture, or if you upload a recording of someone else's voice, make sure you have their permission before you generate.
Independence
omnihuman-2.app is an independent third-party service. It is not affiliated with, endorsed by or sponsored by ByteDance, BytePlus or any other model vendor. Product names and trademarks belong to their respective owners.