Speech for avatars — ASR (speech→text), TTS (text→speech), and Audio2Face-3D lipsync visemes in one import. The voice layer for three.ws avatars.

Give 3D AI agents a voice and a face from any MCP client — text-to-speech, speech-to-text, audio-to-face lipsync (ARKit blendshapes), and the motion-capture clip library. Read-only over the live three.ws API; free NVIDIA lanes, no key required.

Browser-native game runtime — single scene graph, dual renderer (live WebGPU + frame-deterministic WebGPU+WebCodecs), AI-native by design. Substrate behind the AugEngine flagship vertical slice. Built on browser primitives only — no Three.js, no Remotion,

Renderer-agnostic core SDK for Omote AI Characters

Audio-driven facial animation for VRM — convert audio to ARKit blendshapes