GitHub · C++
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.
- Stars
- 4,386
- Forks
- 545
- Stars gained in 24 hours
- +33
- Forks gained in 24 hours
- +10
Topics: ai, amd-gpu, apple-silicon, asr, audio, cpp, edge-ai, ggml, minimax-music3, music-generation
Latest data point: Nov 21, 2026 · 4,386 stars · 545 forks