# PriesiaMioShirakana/DragonianVoice

多个SVC/TTS的C++推理库

Repository: https://github.com/PriesiaMioShirakana/DragonianVoice
Canonical: https://ross.abutalabs.com/products/dragonianvoice
Language: C
License: AGPL-3.0
License Family: copyleft
Topics: pytorch, hifigan, onnxruntime, tacotron2, tts, vits, sovits, diffsvc, diffsinger, rvc, bertvits2, reflowsvc
Last push: 2025-05-18T10:10:18+00:00

## Health v2 (maintenance only)
Score: 40/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 22, release rhythm 28, longevity 100
- inputs: {"age_days": 1489, "days_push": 472, "days_rel": 472, "gap_med": 67, "n_releases_24m": 4}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1129, forks 136 (observed 2026-08-28T04:03:42.123894+00:00)

## What it is
A C++ inference library for running ONNX-based TTS, SVC (singing voice conversion), and SVS (singing voice synthesis) models, supporting architectures like Vits, BertVits2, SoVits, RVC, DiffusionSvc, and DiffSinger. It is callable from C, C++, and C#, and includes a fish-speech.cpp subproject rewritten with the ggml framework.

## Use cases
- run tts models in c++ without python
- convert voice with rvc or so-vits-svc onnx models
- infer diffsinger singing voice synthesis models natively
- embed speech synthesis into a c# application
- run fish-speech inference with ggml

## When to choose
- you need fast native C++ inference for TTS/SVC ONNX models
- you want to integrate voice conversion or synthesis into a C/C++/C# app
- you need CUDA or DirectML acceleration for speech model inference

## When to avoid
- you need to train models rather than run inference
- you want a maintained GUI - the UI is no longer maintained
- you need models or architectures not in the supported list

## Facets
- artifact type: library
- maturity: active
- function: speech-recognition, audio-processing, machine-learning, llm-inference
- domain: speech-processing, machine-learning, deep-learning
- platform: cpp, c, windows, cross-platform
- tags: tts, svc, singing-voice-synthesis, onnxruntime, voice-conversion, vits, rvc, diffsinger, inference-engine, cpp-library, audio, linux, gpu

## Member repositories
- PriesiaMioShirakana/DragonianVoice (main) score 40

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:03:42.123894+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T06:38:23.405618+00:00, confidence not recorded.
  - readme: https://github.com/PriesiaMioShirakana/DragonianVoice (fetched 2026-08-28T04:03:42.123894+00:00, sha 764994ba8bed)
- Data as of 2026-08-30T08:39:29.467469+00:00.