OmniHuman 2.0
Talking avatar
OmniHuman 2.0 — Talking avatar
Animate a portrait with an uploaded voice recording. Add one image and one audio file, review the task settings, and continue in Vizify to create a talking video.
What should I upload? What will I receive?
Explore your idea with AI before generating.
Sign-in and access checks apply in Vizify.
Verified catalog facts
What Vizify exposes for this model family.
These facts are generated from the current public catalog, not copied from provider marketing.
Image · Audio
Video
Talking avatar
Reviewed 2026-11-01
Where this family fits.
Animate a portrait with an uploaded voice recording. Add one image and one audio file, review the task settings, and continue in Vizify to create a talking video.
What not to assume.
Output length follows the recording. Inspect lip sync, motion and identity; exact preservation is not guaranteed.
The current balance check uses the 300-second maximum, rather than a trusted measurement of your recording. Final usage is reconciled after processing. This can require more available balance than a short recording ultimately consumes.
What should I upload?
Upload one portrait image and one WAV or MP3 recording. Audio must be 4–300 seconds and at most 15 MiB; the image upload limit is 10 MiB. A motion instruction is optional, up to 300 characters.
What will I receive?
The task produces a 720p talking-avatar video driven by the audio. It is not a text-to-video workflow, voice clone or image generator.
Capability review
The form and delivery contract were reviewed against the Vizify integration on 2026-11-01. This is not a guarantee of channel availability, speed or output quality.
FAQ
Questions about OmniHuman 2.0 — Talking avatar
What should I upload?
Upload one portrait image and one WAV or MP3 recording. Audio must be 4–300 seconds and at most 15 MiB; the image upload limit is 10 MiB. A motion instruction is optional, up to 300 characters.
What will I receive?
The task produces a 720p talking-avatar video driven by the audio. It is not a text-to-video workflow, voice clone or image generator.
What are the current limits?
Output length follows the recording. Inspect lip sync, motion and identity; exact preservation is not guaranteed.
How is usage estimated?
The current balance check uses the 300-second maximum, rather than a trusted measurement of your recording. Final usage is reconciled after processing. This can require more available balance than a short recording ultimately consumes.