Built a Unity Audio-to-Face workflow — would love some developer feedback

I’ve been testing an audio-driven facial animation workflow for Unity characters.

The basic idea is simple: feed in a WAV file or microphone input, then generate synchronized lip sync and facial animation for an ARKit-ready character.

I’ve been mainly testing:

• lip-sync timing

• mouth movement

• facial expressions

• how simple the Unity setup feels

Here’s a short demo:

Unity repo:
https://github.com/sumeurai/AudioToFace-For-Unity

I’m part of the Mugen3D team, so disclosure up front. I’m mainly interested in hearing what other Unity developers would improve in the workflow or final animation.