AnimaSync

Voice-driven 3D avatar animation engine for the browser.
Lip sync · Facial expressions · Body motion · All from audio alone.

npm V2 npm V1 GitHub

🔊

V1 Data

V1 phoneme engine — 111-dim output mapped to 52 ARKit blendshapes, ONNX inference, real-time visualization.

Try it →

🧑‍🎤

V2 Data

V2 student model — 52 ARKit blendshapes direct prediction, crisp mouth, real-time visualization.

Try it →

⚖️

V1 vs V2

Side-by-side comparison. Same voice, two animation engines, two avatars. See the difference live.

Try it →

3 lines to animate an avatar

import { LipSyncWasmWrapper } from '@goodganglabs/lipsync-wasm-v2';

const lipsync = new LipSyncWasmWrapper();
await lipsync.init();  // 30-day free trial

const result = await lipsync.processFile(audioFile);
const frame = lipsync.getFrame(result, 0); // number[52]
  