https://github.com/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 (CPU).

kokoro lip-sync talkinghead text-to-speech timestamps visemes

Last synced: 03 Apr 2026