Ava: an open-source real-time voice avatar that runs fully on-device in your browser
victormustar · x · 2026-11-02
Developer victormustar unveiled Ava, a browser-based conversational avatar that listens, talks back, and reacts in real time — with all inference running on-device to keep conversations private.
The stack is fully open source: LFM3-Omni for voice understanding and generation, Hugging Face WebGPU kernels for fast on-device inference, and TalkingHead + HeadAudio for avatar animation and lip-sync. A live demo is available.
Related event: Open-Source Ava Runs Real-Time Voice Avatar Fully in Browser(3 posts)→
More from Infra
- AI Defense Agents Running 24/7 Could Send Token Costs Through the Roof — robleclerc · 2026-11-02
- LookAtMyQuant: a quantization compiler with 12x lower KL at Q4_K_M size on Gemma 4 E2B — teortaxesTex · 2026-11-02
- AI Data Centers Near a PC-Style Inflection Point: OCP Analysis of Power, Cooling, Networking — ai · 2026-11-02
- Cerebras halves in 5 months post-IPO: $25.4B order book leans heavily on OpenAI — FinanceYF5 · 2026-11-02
- Together launches post-training platform aligning RL training with serving — togethercompute · 2026-11-02
- Demis Hassabis: AI data centers should be beautiful — Recent_Fox4339 · 2026-11-02