0xShug0 / audio.cpp

An all-in-one, pure C++ inference engine for audio models, powered by ggml. Supports TTS, STT, VAD, voice conversion, music generation, and more, with highly optimized performance. No Python dependency.

Why this job: says: tts, music generation; topics: text-to-speech, tts, asr, voice-cloning, speech-to-text, voice-ai, music-generation

Open on GitHub

What it does

Tired of juggling a dozen Conda environments, hundreds of Python packages, and dependency conflicts just to try a few audio models? audio.cpp gives those paths a shared native runtime instead. Runs on Windows, Linux, and macOS, with support for NVIDIA, AMD, Apple Silicon, and CPU-only machines.

Get started

brew tap 0xShug0/audio-cpp
brew trust 0xShug0/audio-cpp
brew install audio-cpp

Maintenance: Active; Last commit today
Stars: 4,142; +181 this week
Licence: Custom; Read before business use
Downloads for: 2 systems; Mac, Windows
Latest version: v0.9.4; Released 5 days ago
Built with: C++; 88% of the code

Is it looked after?

Contributors: 22; Last 90 days
Issues: 98% closed; 7 still open
Pull requests: 779 merged; 7 waiting
Releases: 25; 25 in the last year

Contributing guide (opens in new tab)
No security policy
No code of conduct

Similar repos

Repos similar to this one
Repo	Stars	Last commit	Licence	Downloads for
kigner / audio.cpp-webui	421	5 days ago	Custom	No downloads
IAHispano / Applio	3,984	6 days ago	MIT	No downloads
AutoArk / GPA	3,056	5 months ago	Apache-2.0	No downloads

More: download files, languages, topics and project record

Download files, v0.9.4

Mac4 files, 583 downloads
Windows15 files, 11,123 downloads

All files on GitHub (opens in new tab)

Languages

C++ 88%
Python 9%
Svelte 1%
CMake 1%

Topics

ai
amd-gpu
apple-silicon
asr
audio
cpp
edge-ai
ggml
minimax-music3
music-generation
speech-analysis
speech-to-speech

Project record

JobSpeech and audio
StatusListed
Commits1,217
Forks502
Watching33
Stars in 28 days+656
CreatedJun 23, 2026
First seen by usNov 7, 2026
CheckedNov 10, 2026