huggingface /
speech-to-speech
Build voice agents with open-source models
Updated 37 min ago
+71 stars gained this week
Stars gained each day, last 30 days
Usual pace · 10 / day
Oct 4Oct 19Today
This week Before Usual pace
In short
A voice agent that runs fully on your own computer with open-source models for speech detection, transcription, language, and synthesis. It also serves the OpenAI Realtime protocol for apps that want a local backend.
Summary written by AI from the repository’s description and README.
huggingface / speech-to-speech
View on GitHub(opens in new tab)