# FACEGOOD/FACEGOOD-Audio2Face

http://www.facegood.ai

Repository: https://github.com/FACEGOOD/FACEGOOD-Audio2Face
Canonical: https://ross.abutalabs.com/products/facegood-audio2face
Language: Python
License: MIT
License Family: permissive
Last push: 2026-03-11T14:38:20+00:00

## Health v2 (maintenance only)
Score: 64/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 71, release rhythm 35, longevity 100
- inputs: {"age_days": 1715, "days_push": 175, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1909, forks 365 (observed 2026-08-28T04:05:53.053674+00:00)

## What it is
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
- artifact type: library
- maturity: active
- function: machine-learning, deep-learning, audio-processing, speech-recognition, animation
- domain: machine-learning, deep-learning, graphics
- platform: windows, python, cpp, game-engine
- tags: audio2face, blendshapes, facial-animation, digital-humans, unreal-engine, lpc, maya, inference, audio, game-development

## Member repositories
- FACEGOOD/FACEGOOD-Audio2Face (main) score 64

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:05:53.053674+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T03:11:05.810049+00:00, confidence not recorded.
  - readme: https://github.com/FACEGOOD/FACEGOOD-Audio2Face (fetched 2026-08-28T04:05:53.053674+00:00, sha b91080c89dd0)
- Data as of 2026-08-30T08:39:29.467469+00:00.