ShawnPi233/HQ-SVC
Official Repository of Paper: "Towards High-Quality Zero-Shot Singing Voice Conversion in Low-Resource Scenarios"(AAAI 2026)
HQ-SVC helps musicians, content creators, and audio engineers convert a singing voice from one person to another, even for singers it hasn't heard before. You provide an original singing performance and a short audio clip of the target singer's voice, and it outputs the original performance sung in the target voice with high fidelity. It can also enhance the quality of low-resolution singing voice recordings.
Use this if you need to transform a singing voice into another without needing extensive training data for the new voice, especially when working with limited computational resources.
Not ideal if you require control over singing style or if you're looking for a solution that runs on Windows without WSL.
Stars
91
Forks
5
Language
Python
License
—
Category
Last pushed
Jan 31, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/voice-ai/ShawnPi233/HQ-SVC"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
yeyupiaoling/MASR
Pytorch实现的流式与非流式的自动语音识别框架，同时兼容在线和离线识别，目前支持Conformer、Squeezeformer、DeepSpeech2模型，支持多种数据增强方法。
shivammehta25/Matcha-TTS
[ICASSP 2024] 🍵 Matcha-TTS: A fast TTS architecture with conditional flow matching
coqui-ai/TTS
🐸💬 - a deep learning toolkit for Text-to-Speech, battle-tested in research and production
DigitalPhonetics/IMS-Toucan
Controllable and fast Text-to-Speech for over 7000 languages!
gabrielmittag/NISQA
NISQA - Non-Intrusive Speech Quality and TTS Naturalness Assessment