Skip to content

JoyGen

Generate talking-face video from audio

Visit official site

What JoyGen is

The technique is described as audio-driven 3D depth-aware talking-face video generation that pairs lip motion with appearance synthesis.

What you can do with it

  • Generate a talking-face video for a virtual host
  • Create character speaking animation for animation work
  • Make a teacher speaking video for online education

What to watch out for

  • The workflow needs a clear input audio clip
  • A face depth map is used in the synthesis stage
  • A two-stage framework is described

Pros & cons

✓ What we like

  • Chinese and English and other languages are supported
  • A large Chinese talking-face dataset is provided

! What to watch out for

  • The workflow needs a clear input audio clip
  • A face depth map is used in the synthesis stage

FAQ

What are the two stages?

Audio-driven lip motion generation and visual appearance synthesis.

Which languages are named?

Chinese and English are named among the supported languages.

Last reviewed: 2026-11-15

More AI video generation tools

View all →

How we review