# innnky/so-vits-svc

基于vits与softvc的歌声音色转换模型

Repository: https://github.com/innnky/so-vits-svc
Canonical: https://ross.abutalabs.com/products/innnky-so-vits-svc
Language: Python
License: AGPL-3.0
License Family: copyleft
Archived: true
Last push: 2024-10-19T16:16:34+00:00

## Health v2 (maintenance only)
Score: 10/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 0, release rhythm 35, longevity 100
- inputs: {"age_days": 1445, "days_push": 683, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases, archived
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 3779, forks 27 (observed 2026-08-28T04:08:18.383830+00:00)

## What it is
A singing voice conversion (SVC) framework that uses a SoftVC content encoder with VITS to transform one singer's voice into another timbre. It is a Python training and inference framework requiring users to train their own models, and it has been officially archived in favor of the community-maintained so-vits-svc fork.

## Use cases
- convert a song into another singer's voice
- train a custom singing voice conversion model
- change the timbre of vocal audio offline
- make AI cover songs with a target voice
- run singing voice conversion on a GPU locally

## When to choose
- you want to train a custom singing voice conversion model from your own authorized dataset
- you need fully offline voice conversion with no data sent anywhere
- you want faster inference than DiffSVC on moderate-quality datasets

## When to avoid
- you need active maintenance or bug fixes - the repo is archived
- you want a ready-to-use pretrained voice model out of the box
- you need production-grade speech synthesis rather than a research framework
- you cannot resolve dataset licensing for training data

## Facets
- artifact type: library
- maturity: abandoned
- function: speech-recognition, audio-processing, machine-learning, deep-learning, llm-training
- domain: machine-learning, artificial-intelligence, speech-processing
- platform: python, cross-platform
- tags: singing-voice-conversion, voice-conversion, vits, so-vits-svc, hifigan, audio-synthesis, archived, audio, gpu

## Member repositories
- innnky/so-vits-svc (main) score 10

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:08:18.383830+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-29T18:27:46.736978+00:00, confidence not recorded.
  - readme: https://github.com/innnky/so-vits-svc (fetched 2026-08-28T04:08:18.383830+00:00, sha b203a93edd36)
- Data as of 2026-08-30T08:39:29.467469+00:00.