Back to Tools Directory
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.
Categories & Topics
audio-modelsttssttinference-enginevoice-conversionaiamd-gpuapple-siliconasraudioaudio-analysiscppedge-aiggmlminimax-music3music-generationspeech-analysisspeech-to-speechspeech-to-texttext-to-speechvoice-cloningvulkanyue2
Repository Stats
2.9k
GitHub Stars
330
Forks
2.9k
Watchers
16
Open Issues
License
Other
Repository
0xShug0/audio.cppLast Updated
Today
September 21, 2026
Latest Release
v0.8.1
3 days ago
