svc-develop-team/so-vits-svc

Health v2 · maintenance only

Flags: no_releases archived

Adoption not part of the score

28125 stars · 5034 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-29, confidence not recorded

A deep learning framework based on SoftVC VITS for singing voice conversion (SVC), letting users train models that convert one singing voice into another. It runs fully offline in Python with PyTorch and is now archived.

Use cases

• convert a singing voice to sound like another singer
• train an AI voice model from song recordings
• make anime characters sing with a custom voice
• offline singing voice conversion with pytorch
• create AI covers of songs

When to choose

• you want to train or run singing voice conversion models offline
• you need a well-known SVC framework with community forks and tooling
• you are comfortable with Python and GPU training workflows

When to avoid

• you need text-to-speech - this project does not support TTS
• you want an actively maintained upstream repo - it is archived
• you want a polished GUI - use forks like so-vits-svc-fork or MoeVoiceStudio instead

Facets

library · maturity maintenance

audio-processing machine-learning deep-learning speech-recognition machine-learning deep-learning artificial-intelligence python cross-platform singing-voice-conversion vits voice-changer pytorch generative-adversarial-network voice-conversion so-vits-svc audio gpu

Member repositories

For agents

markdown · JSON · MCP: product_card(name="svc-develop-team/so-vits-svc")