voicepaw/so-vits-svc-fork
so-vits-svc fork with realtime support, improved interface and more features.
This tool helps musicians, content creators, and performers transform their singing or speaking voice in real-time or from audio files. You provide your voice (live through a microphone or a pre-recorded WAV file) and a pre-trained voice model, and it outputs your performance with the characteristics of the chosen voice. It's designed for anyone looking to alter their vocal identity for creative projects.
9,281 stars. Used by 1 other package. Actively maintained with 24 commits in the last 30 days. Available on PyPI.
Use this if you need to convert a singing or speaking voice into another voice model instantly for live performances, streaming, or quick audio editing.
Not ideal if you are looking for the absolute cutting-edge in voice conversion technology with the latest research improvements, as this project is no longer actively maintained.
Stars
9,281
Forks
1,236
Language
Python
License
—
Category
Last pushed
Mar 13, 2026
Commits (30d)
24
Dependencies
25
Reverse dependents
1
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/voice-ai/voicepaw/so-vits-svc-fork"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Recent Releases
Compare
Related tools
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。
coqui-ai/TTS
🐸💬 - a deep learning toolkit for Text-to-Speech, battle-tested in research and production
shivammehta25/Matcha-TTS
[ICASSP 2024] 🍵 Matcha-TTS: A fast TTS architecture with conditional flow matching
DigitalPhonetics/IMS-Toucan
Controllable and fast Text-to-Speech for over 7000 languages!
gabrielmittag/NISQA
NISQA - Non-Intrusive Speech Quality and TTS Naturalness Assessment