Hugging Face open-sources a local speech-to-speech voice-agent stack

huggingface · github · 2026-07-28

Hugging Face released speech-to-speech, a Python project for building local voice agents with open-source models.

The repo combines speech-to-text, speech synthesis, and speech translation components, aiming to make fully local voice-agent workflows easier to prototype and run.

Original post →

More from coding & agent

coding & agent channel →