Portrait Image to Talking Video
omnihuman_1_5
Estimated from selected length; voice track controls pacing
Requires one portrait image URL, one speech audio URL and a short behavior prompt.
Open routeUlazAI - AI Image & Video Tools
Premium talking portrait model
OmniHuman 1.5 talking portrait generator
Turn a portrait or character image into a speaking video driven by a speech audio file. This is the route to use when identity and facial performance matter more than full-scene generation.
27 credits/s. Studio output is configured for 1080.
Founder videos, product explainers and localized spokesperson clips.
Character-led education where the same face needs multiple scripts.
Portrait animation where mouth movement, expression and audio timing matter.
Marketing proof reel
Explanation, examples, and benefits in one launch video
Use this as the fast read before choosing a route: it explains the input logic, shows generated examples, and gives the commercial reason to test the model in Video Studio.
Explanation Pick the route from the input you already have.
Example Watch real generated clips instead of abstract claims.
Benefits Clear prompts, clear pricing, clear next step.
Where it fits
OmniHuman starts from a portrait image and speech audio. Lip sync starts from an existing video and changes the mouth timing to match new audio.
| Duration | 720p / base | 1080p |
|---|---|---|
| 5s | 135 credits | - |
| 10s | 270 credits | - |
| 30s | 810 credits | - |
| 60s | 1620 credits | - |
Studio routes
How it differs from lip sync
OmniHuman starts from a portrait image and speech audio. Lip sync starts from an existing video and changes the mouth timing to match new audio.
Production workflow
- Choose a clear portrait image with good face visibility.
- Prepare clean speech audio with the exact script.
- Write a short behavior prompt: tone, expression and natural movement.
- Generate the clip, then reuse the same portrait for more scripts.
FAQ
What does OmniHuman need?
One portrait image URL, one speech audio URL and a prompt for expression or behavior.
Is the helper detection tooling a video model?
No. The Studio route is the video generation route; detection helpers are separate checks and are not exposed as video models.