# nomadkaraoke/python-audio-separator

Easy to use stem (e.g. instrumental/vocals) separation from CLI or as a python package, using a variety of amazing pre-trained models (primarily from UVR)

Repository: https://github.com/nomadkaraoke/python-audio-separator
Canonical: https://ross.abutalabs.com/products/python-audio-separator
Language: Python
License: MIT
License Family: permissive
Last push: 2026-07-20T22:02:46+00:00

## Health v2 (maintenance only)
Score: 89/100 (v2, computed 2026-09-03T02:39:23.370411+00:00)
- activity 93, release rhythm 87, longevity 82
- inputs: {"age_days": 1160, "days_push": 44, "days_rel": 7, "gap_med": 2, "n_releases_24m": 62}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1327, forks 193 (observed 2026-08-28T04:04:22.938944+00:00)

## What it is
A Python package and CLI that separates audio files into stems (vocals, instrumental, drums, bass, etc.) using pre-trained models from Ultimate Vocal Remover such as MDX-Net, VR Arch, Demucs, and MDXC. It supports GPU acceleration via CUDA, CoreML, and DirectML, and can also perform denoising and reverb removal.

## Use cases
- separate vocals from instrumental in a song
- make karaoke tracks from mp3 files
- split a song into drums bass and guitar stems
- remove reverb or echo from audio recordings
- batch separate audio stems from the command line
- integrate stem separation into a python app

## When to choose
- you need vocal/instrumental separation with a simple CLI or Python API
- you want access to many UVR pre-trained models without building a GUI
- you have a CUDA GPU, Apple Silicon, or want CPU fallback
- you are producing karaoke videos or remixing stems

## When to avoid
- you need a graphical interface for stem separation (use UVR directly)
- you need real-time live audio separation
- you want general-purpose audio editing beyond stem separation

## Facets
- artifact type: library
- maturity: active
- function: audio-processing, machine-learning, cli, gpu-computing
- domain: machine-learning, media, developer-tools
- platform: python, cli, cross-platform
- tags: stem-separation, vocal-removal, karaoke, uvr-models, demucs, mdx-net, instrumental-separation, audio-denoising, audio, gpu, docker

## Member repositories
- nomadkaraoke/python-audio-separator (main) score 89

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:04:22.938944+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 2026-08-30T04:46:18.522932+00:00, confidence not recorded.
  - readme: https://github.com/nomadkaraoke/python-audio-separator (fetched 2026-08-28T04:04:22.938944+00:00, sha 3a1d04c51543)
- Data as of 2026-08-30T08:39:29.467469+00:00.