huggingface/speech-to-speech: Build local voice agents with open-source models
Why CEREBRO kept it
Local voice agents with open models
The text below is an automated extraction of the article at https://github.com/huggingface/speech-to-speech, stored verbatim in the public cerebro-vault repository. Copyright remains with the original publisher (github.com).
A low-latency, fully modular voice-agent pipeline: VAD -> STT -> LLM -> TTS, exposed through an OpenAI Realtime-compatible WebSocket API. Every component is swappable. The LLM slot speaks OpenAI-compatible protocols, so you can point it at a hosted provider, at HF Inference Providers, or at a vLLM or llama.cpp server on your own hardware for a fully local, fully open stack. This pipeline runs in production as the conversation backend for thousands of Reachy Mini robots. pip install speech-to-speech export OPENAI_API_KEY=... speech-to-speechThis starts an OpenAI Realtime-compatible server at
Backlinks
Appeared in 3 briefings