PriesiaMioShirakana/DragonianVoice
A C++ ONNX inference library supporting multiple TTS and singing voice conversion models including VITS, RVC, DiffSinger, and BERTVits2.
Velocity · 7d
+0.8
★ / day
Trend
→steady
star history
This repository provides C/C++/C# callable inference engines for a range of voice synthesis models. It supports TTS models (Tacotron2, VITS, BERTVits2, GPtSoVits), SVC models (SoVitsSvc, RVC, DiffusionSvc, FishDiffusion, ReflowSvc), and SVS models (DiffSinger), all running via ONNX runtime. A ggml-based rewrite of fish-speech (fish-speech.cpp) is also included for hardware-accelerated inference.