v0.12.0 v0.12.1

Name: speech-to-speech
Author: huggingface

huggingface/speech-to-speechAug 12, 2026 → Aug 12, 20260 days between releases

Generating AI comparison

Analyzing what changed between v0.12.0 and v0.12.1. This page updates automatically — usually within a minute.

The Two Releases

v0.12.0

Aug 12, 2026· 2 months ago

A major feature release introducing multi-stream SIP legs, Google Cloud Storage backend, and Deepgram Flux integration, along with improved audio resampling and recording handling.

Full release notes

v0.12.1

Aug 12, 2026· 2 months ago

A patch release focused on stability, specifically fixing a flaky test case related to speech-to-text turn detection.

Full release notes