OpenViSTAI · Agents · Blockchain · Crypto
Submit a project
Menu
Audio & Voice AI

So Vits Svc Fork

So Vits Svc Fork is a Python application that converts singing voices using the SoftVC VITS approach. It adds real-time conversion support and offers both a graphical interface and a unified command-line interface. The project states that compatible models are based on so-vits-svc branch 4.0; it excludes 4.1 and other models.

Explore the practical guide ↓

Independent OpenViST project profile, based on linked sources.

So Vits Svc Fork — OpenViST project profile in Audio & Voice AI.
OpenViST project illustration. See the linked sources for product details.
Understand the project

Practical overview

When it fits

Consider it when you need real-time singing voice conversion and have a model based on the supported so-vits-svc 4.0 branch. Review its installation notes and maintenance status before adopting it.

Who it is for

  • People seeking a desktop interface for singing voice conversion.
  • Users who want to work with compatible SoftVC VITS models through a GUI or command line.
  • Developers evaluating a Python-based voice-conversion application with real-time processing.

Documented uses

  • Convert singing voices using a compatible model.
  • Choose a graphical or command-line workflow for inference.
  • Set up the application with a documented Python and PyTorch installation path.
Before you choose

Requirements & limits

  • The README excludes so-vits-svc 4.1 models and other model versions.
  • The project is no longer maintained, with updates limited to maintenance since Spring 2023.
  • Manual pipx installation is marked experimental; the README also documents a Windows batch installer and a manual pip route.
  • Installation instructions vary by operating system and GPU setup.

Check current requirements in the official documentation. Source-based guidance does not mean OpenViST has run or independently tested this project.

Source-based practical guide

Install the application manually with pip

Set up the package in a Python 3.11 virtual environment with PyTorch dependencies.

Before you start

  • Python 3.11
  • A command-line shell
  • For the documented CUDA route, a supported NVIDIA GPU and the PyTorch CUDA 12.1 package index

Steps

  1. Create and activate a Python 3.11 virtual environment using the commands documented for your operating system, or use the documented Anaconda environment setup.

  2. Upgrade pip, setuptools and wheel.

  3. Install torch and torchaudio from the documented CUDA 12.1 package index, or omit that GPU-specific installation command for the documented no-GPU or macOS case.

  4. Install so-vits-svc-fork with pip.

Expected outcome

The package and its documented PyTorch dependencies are installed in the chosen environment.

Guide limitations

  • This covers installation only, not running inference.
  • The README says AMD GPUs are not supported on Windows; its AMD Linux instructions use a different PyTorch package index.
  • The README describes MPS support as probable rather than guaranteed.
Documentation 1 ↗
Evidence and transparency

Sources & review

Official repository ↗
Source record details
Source availability
Active
Sources checked
16 October 2026
Original website title
voicepaw/so-vits-svc-fork · Official homepage title · retained in its source language
How we review sourcesSuggest a correction