met4citizen/HeadTTS
HeadTTS: Free neural text-to-speech (Kokoro) with timestamps and visemes for lip-sync. Runs in-browser (WebGPU/WASM) or on local Node.js WebSocket/REST server (WebGPU/CPU).
GitHub repository with 182 stars and 25 forks.
Language: JavaScript
Topics: kokoro, lip-sync, talkinghead, text-to-speech, timestamps, visemes