Audio Separator nomadkaraoke/python-audio-separator

Command-line tool and Python package that splits audio into vocals, instrumental and other stems using UVR, Demucs and RoFormer models.

Creator kit + Compare GitHub ↗ Install guide (official) ↗

Audio Separator at a glance

Checked 16 Oct 2026

Audio Separator is a pip-installable CLI and Python library that runs the stem-separation models used in Ultimate Vocal Remover (MDX-Net, VR, Demucs, MDXC/RoFormer). It does two-stem vocal/instrumental splits and more stems such as drums, bass, piano and guitar, on NVIDIA CUDA, Apple Silicon, CPU or experimental DirectML, and ships Docker images. Code is MIT; licences of the non-UVR models it downloads are not stated in one place. There is no GUI, and it does not generate music.

Cite this pageRepoQuarry. “Audio Separator.” Checked 16 Oct 2026. https://repoquarry.dev/projects/python-audio-separator

How much of Suno does it replace?

1 of 5 jobs. Splits any song into stems from the command line or Python; no generation.

Full songs with vocals from a prompt or lyrics Not covered

Instrumental tracks (Instrumental mode) Not covered

Covers and restyles of an uploaded song (Cover) Not covered

Extending or regenerating part of a song (Extend Not covered

Splitting a song into vocal and instrument stems (Get Stems) Full replacement

For full songs with vocals from a prompt or lyrics, instrumental tracks (Instrumental mode), covers and restyles of an uploaded song (Cover), extending or regenerating part of a song (Extend, see other Suno alternatives. You may also need to build an interface, an API server and hosting yourself.

Facts, with sources

Every answer links to where we found it. We read the documentation; we did not install it.

Report a correction

QuestionAnswerSourceChecked

Runs on my machine? Yes, CLI, Python package or Docker Easy to use audio stem separation from the command line or as a dependency in your own Python project github.com · python-audio-separator#installation-%EF%B8%8F ↗ 1d ago

Code licence MIT This project is licensed under the MIT License. github.com · python-audio-separator#license- ↗ 1d ago

Model weights licence The README identifies MIT with UVR credit for UVR-trained models; a complete licence inventory for every other downloadable model, including RoFormer variants, was not verified github.com · python-audio-separator#license ↗ today

Commercial use MIT permits use of the wrapper code; commercial permission remains dependent on the selected model. The README's UVR attribution statement does not establish the terms for every downloadable weight github.com · python-audio-separator#license ↗ today

Paid services needed? None required; an optional remote API can be self-deployed on Modal To deploy Audio Separator as an API on modal.com and use this for remote processing github.com · python-audio-separator#remote-api-usage- ↗ 1d ago

Hardware CPU-only works; NVIDIA CUDA, Apple Silicon (macOS 14+) and experimental DirectML acceleration No hardware acceleration, CPU only github.com · python-audio-separator#-no-hardware-acceleration-cpu-only ↗ 1d ago

Operating systems Linux, macOS (Apple Silicon) and Windows; Docker images for amd64 and arm64 images published on Docker Hub for GPU (CUDA) and CPU inferencing, for both amd64 and arm64 platforms. github.com · python-audio-separator#installation-%EF%B8%8F ↗ 1d ago

Setup effort Easy; pip install audio-separator (CPU or GPU extra) or Docker; FFmpeg needed pip install "audio-separator[cpu]" github.com · python-audio-separator#-no-hardware-acceleration-cpu-only ↗ 1d ago