#4848th of 67 in VoiceFor voice, speech and music
so-vits-svc-fork
Singing voice conversion with realtime mic input, GUI and CLI training
- Stars
- 9.3k
- License
- custom license
- Last commit
- Oct 2026
- Last release
- Feb 2026
- Language
- Python
9,184 on 10 Apr 20269,331 on 30 Oct 2026
From GitHub's daily star counts.
Checked on GitHub.
Overview
Fork of so-vits-svc 4.0 (v1) that converts a voice to a trained target speaker, from files or live microphone input, using the `svcg` GUI or the `svc` CLI. It adds CREPE pitch estimation, a ContentVec fix, QuickVC's MS-iSTFT decoder and pip installation with automatic pretrained model download. The README states it is no longer maintained and has been in maintenance only since Spring 2023.
Who it is for: People training or running legacy so-vits-svc 4.0 voice models
Strengths
- Realtime conversion from microphone via `svc vc`, plus file inference with `svc infer`
- Installs with pip; pretrained models download automatically, no fairseq needed
- Full CLI pipeline for preprocessing, splitting, diarization and training
- CPU inference supported; GPU inference and training need at least 4 GB VRAM
Weaknesses
- README declares the project no longer maintained, since Spring 2023
- Only 4.0v1 models are compatible; 4.1 and other models are unsupported
- ONNX export is listed as currently not working
- AMD GPUs unsupported on Windows; Linux needs a ROCm build of PyTorch
What it needs
- GPU optional
- Docker
- Needs PyTorch, torchaudio, Python 3.11, pyannote.audio (optional, for diarization)
- Models: so-vits-svc 4.0v1, QuickVC (MS-iSTFT decoder), ContentVec, HuBERT, CREPE
Quick answers
Is so-vits-svc-fork open source?
Its code is public on GitHub under its own license terms; read them before you use it at work.
Can you run so-vits-svc-fork with Docker?
Yes. Its repository has a Docker setup: a Dockerfile, a Compose file or a published image.
Does so-vits-svc-fork need a GPU?
No. It runs on a CPU and can use a GPU when you have one.
Also in Voice
See all 67| Rank | Project | Score |
|---|---|---|
| 1 | voicestudioDesktop app for voice cloning, dubbing, dictation and audiobooks | 97 out of 100 |
| 2 | whisper.cppC/C++ port of OpenAI Whisper for local speech-to-text transcription | 89 out of 100 |
| 3 | handyOffline push-to-talk dictation app that pastes transcripts into any text field | 89 out of 100 |
| #4 | xiaozhi-esp32ESP32 firmware for a voice chatbot with MCP device and cloud tool control | 82 out of 100 |
| #5 | buzzOffline desktop app for transcribing and translating audio with Whisper | 81 out of 100 |