FACEGOOD/FACEGOOD-Audio2Face

Health v2 · maintenance only

Flags: no_releases

Adoption not part of the score

1909 stars · 365 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-30, confidence not recorded

FACEGOOD Audio2Face is an open-source deep learning framework that converts audio into facial blendshape weights for driving digital humans, primarily in Unreal Engine. It includes training scripts, a pretrained model, and a test application for real-time audio-driven facial animation.

Use cases

• generate facial animation from audio
• drive a digital human avatar with voice in Unreal Engine
• train a custom audio-to-blendshape model
• real-time lip sync from microphone input
• create talking digital humans for games or virtual assistants

When to choose

• you need audio-driven facial animation with blendshape rigs
• you work in Unreal Engine or Maya pipelines
• you want to train a custom lip-sync model on your own recorded data

When to avoid

• you need full head or body animation, not just blendshape weights
• you want a polished commercial product without training your own model
• you need non-Windows production tooling out of the box

Facets

library · maturity active

machine-learning deep-learning audio-processing speech-recognition animation machine-learning deep-learning graphics windows python cpp game-engine audio2face blendshapes facial-animation digital-humans unreal-engine lpc maya inference audio game-development

Member repositories

For agents

markdown · JSON · MCP: product_card(name="FACEGOOD/FACEGOOD-Audio2Face")