Hugging Face open sources a real-time speech-to-speech voice-agent pipeline
anselm · x · 2026-07-28
Hugging Face open sourced Speech to Speech, a modular real-time voice-agent pipeline that can run locally on a GPU.
- The stack chains VAD → STT → LLM → TTS and exposes an OpenAI Realtime-compatible WebSocket API.
- Each component is swappable, so the LLM can point to a hosted provider, HF Inference Providers, or a local vLLM / llama.cpp server.
- The project aims to remove the latency and billing complexity of proprietary voice APIs such as OpenAI Realtime, ElevenLabs, and Google Cloud.
- The repo image says the pipeline is already in production as the conversation backend for thousands of Reachy Mini robots.
More from coding & agent
- Vibe coding looks unserious until people start shipping real apps with it — alexmacgregor__ · 2026-07-28
- StateAct: Program State Cuts Agent Costs by 9x, Sets New SOTA — _akhaliq · 2026-07-28
- Open-source AI Skill turns The Art of War into a structured decision workflow for Claude Code — yangyi · 2026-07-28
- Who is liable when an AI agent uses non-commercial software on your behalf? — gabepgomes · 2026-07-28
- Voice may replace keyboards as the main interface for managing agents and computers — noahsolomon · 2026-07-28
- Custom scripts often beat waiting for a better MCP, says one AI workflow user — DavidWells · 2026-07-28