Hugging Face Open-Sources Local Voice Agent Pipeline Compatible with OpenAI Realtime API
techNmak · x · 2026-08-03
Hugging Face released a repository for building fully local voice assistants that listen, think, and speak back using entirely open-source models.
- Modular Pipeline: Runs four stages in separate threads: Voice Activity Detection (VAD), Speech-to-Text (STT), an LLM, and Text-to-Speech (TTS).
- Swappable Components: Every stage is interchangeable via CLI flags, and the LLM slot accepts any OpenAI-compatible endpoint.
- API Compatible: Exposed via a WebSocket API that is fully compatible with OpenAI's Realtime API protocol.
- Production Ready: Already deployed as the conversational backend for thousands of Reachy Mini robots. Can be installed with a single pip install speech-to-speech command.
More from coding & agent
- CAPA: Benchmarking Cross-Session Memory for AI Coding Assistants — HKUST · 2026-08-03
- Open-Source Library Installs 165 Pedagogical Skills into Claude and Codex Agents — azed_ai · 2026-08-03
- Developer Builds Browser 3D Shooter with GPT, Attracts Over 100 Players at Indie Event — WranglerObvious5932 · 2026-08-03
- TabAPI launches: one API for traffic, WHOIS, DNS, and more — sujingshen · 2026-08-03
- Emerging Markdown Formats Reshape Coding Agent Behavior — bibryam · 2026-08-03
- Cloudflare Kicks Off Agents Week: Envisioning an 'Agent Cloud' for Autonomous AI — threepointone · 2026-08-03