Nine open-source voice and audio AI repos you can run right now

JafarNajafov · x · 2026-07-24

This post rounds up nine GitHub repositories for voice and audio AI that you can run today, spanning speech recognition, text-to-speech, voice cloning, and inference optimization.

The list includes Whisper, F5-TTS, Coqui TTS, RVC, Bark, OpenVoice, whisper.cpp, Faster Whisper, and ChatTTS. It is framed as a practical bookmark set for people looking to experiment with open-source audio pipelines rather than a model announcement.

Original post →

More from Multimodal

Multimodal channel →