Real-time voice AI fully in-browser: WebGPU kernels + LFM3-Omni demo
victormustar · x · 2026-11-02
- Developer victormustar demoed Ava, a real-time talking-avatar voice assistant running entirely in the browser with no backend: Liquid AI's LFM3-Omni model, TalkingHead + HeadAudio for the avatar, and custom WebGPU kernels for on-device inference speed.
- It builds on the growing Hugging Face webgpu-kernels ecosystem with 200+ ONNX operator implementations running on browser GPUs.
- A live interactive demo is available; the pitch: build tomorrow's experiences with custom WebGPU kernels today.
Related event: Open-Source Ava Runs Real-Time Voice Avatar Fully in Browser(3 posts)→
More from coding & agent
- Stardock CEO uses AI agents to animate game characters without rigging, runs 101 agents — draginol · 2026-11-02
- Stardock CEO runs 101 AI agents like a studio: inside his Clairvoyance workflow — draginol · 2026-11-02
- DeepSeek's SuperAgent architecture questioned over risky multi-worker event design — teortaxesTex · 2026-11-02
- Dev wires watch button to record, upload, and let Grok Bot delegate voice tasks — johnlindquist · 2026-11-02
- Matt Pocock: Redux's single-source-of-state idea may be exactly what agents need — mattpocockuk · 2026-11-02
- Game2Player: builders and players co-develop 568 games to train a 9B visual agent — ManlingLi_ · 2026-11-02