# Plachtaa/seed-vc

zero-shot voice conversion & singing voice conversion, with real-time support

Repository: https://github.com/Plachtaa/seed-vc
Canonical: https://ross.abutalabs.com/products/seed-vc
Language: Python
License: GPL-3.0
License Family: copyleft
Topics: voice-conversion, singing-voice-conversion
Archived: true
Last push: 2025-04-20T05:27:10+00:00

## Health v2 (maintenance only)
Score: 10/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 17, release rhythm 35, longevity 52
- inputs: {"age_days": 729, "days_push": 500, "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 3888, forks 532 (observed 2026-08-28T04:08:28.310046+00:00)

## What it is
Seed-VC is a Python tool and model for zero-shot voice conversion, real-time voice conversion, and singing voice conversion, cloning a voice from just 1-30 seconds of reference audio without training. It also supports fast fine-tuning on custom speaker data and runs on Windows, Linux, and Apple Silicon Macs.

## Use cases
- convert my voice to sound like someone else in real time
- clone a voice from a short audio sample
- convert a song to sing in another person's voice
- real-time voice changer for streaming or gaming
- fine-tune a voice conversion model on a custom speaker
- zero-shot voice conversion without training a model

## When to avoid
- you need text-to-speech from text rather than conversion from existing audio
- you require a permissive license for commercial products (GPL-3.0)
- you need offline batch processing on CPU-only hardware with low latency

## Facets
- artifact type: library
- maturity: active
- function: audio-processing, machine-learning, deep-learning, speech-recognition, cli
- domain: machine-learning, deep-learning, artificial-intelligence
- platform: python, windows, cli
- tags: voice-conversion, singing-voice-conversion, voice-cloning, zero-shot, real-time-audio, tts-adjacent, fine-tuning, audio, linux, macos, gpu

## Member repositories
- Plachtaa/seed-vc (main) score 10

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:08:28.310046+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 2026-08-29T18:25:38.412647+00:00, confidence not recorded.
  - readme: https://github.com/Plachtaa/seed-vc (fetched 2026-08-28T04:08:28.310046+00:00, sha cf284718d6ec)
  - registry_pypi: https://pypi.org/pypi/seed-vc/json (fetched 2026-08-29T09:19:30.871220+00:00, sha fe45f2d264de)
- Data as of 2026-08-30T08:39:29.467469+00:00.