GitHub
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.
On GitGem
Written in C++, licensed under Custom.
It gained 203 stars in the past week, about 29 a day. It has been tracked on GitGem.org since July 1, 2026.
See the C++ trending boardStars
804
Forks
92
Open Issues
9
Language
C++
License
Custom
Last Commit
4h ago
Comments
No comments yet. Be the first!
You will sign in with GitHub to post. Your draft is kept.