Skip to content

AniPortrait

Animate a still face to speak or sing from audio

Visit official site

What AniPortrait is

The framework is described as a project that generates talking and singing videos from audio and image input. It turns audio and a static face photo into realistic face animation with matching lip movement, and supports multiple languages, face re-drawing and head pose control.

What you can do with it

  • Synthesise animation driven by audio
  • Re-enact a face from a still portrait
  • Control head pose
  • Generate video from self-driven or audio-driven input
  • Produce high-quality animation with matching lip movement
  • Configure models and weights flexibly

Application scenarios

  • Generate a video of a face that talks
  • Generate a realistic animation of a face singing
  • Apply the face re-enactment effect

Pros & cons

✓ What we like

  • Lip movement is kept in sync with the audio
  • Flexible model and weight configuration

! What to watch out for

  • Animation is driven by the supplied audio and a static face image
  • The listed outputs centre on talking and singing face videos

FAQ

What inputs does it need?

The source names audio and a static face image as the inputs.

Does it control head pose?

Yes, head pose control is listed among the features.

Last reviewed: 2026-11-15

More AI video generation tools

View all →

How we review