---
id: demucs
version: "4.1.0"
license: MIT License
license_treatment: permissive
maintenance: active
---

# demucs — Music source separation in the waveform domain.

License: permissive · Maintenance: active · Downloads: 400.5K/mo

## What it is and what it does

Demucs is a music source separation model that breaks a single audio track into isolated stems—drums, bass, vocals, and other accompaniment. Version 4 uses a hybrid transformer architecture that processes both waveform and spectrogram representations simultaneously, achieving state-of-the-art separation quality (9.0 dB SDR on the MUSDB HQ test set). The model was trained on MUSDB HQ plus 800 additional songs.

You invoke it via command-line or Python API to process MP3, WAV, or other audio formats. It outputs separate audio files for each stem. The package includes multiple model variants: htdemucs_ft (fine-tuned, recommended), htdemucs (baseline), hdemucs_mmi (retrained), and an experimental 6-source model. Separation runs on CPU or GPU; GPU is significantly faster but not required.

Use it for:

- Extract vocals from a song for karaoke or vocal-focused remixing workflows.
- Isolate drum and bass tracks for beat analysis, re-arrangement, or music production.
- Create instrumental versions by removing vocals for background music or licensing.
- Prepare training data for music information retrieval or other audio ML tasks.
- Analyze song composition by examining separated stems independently.

## Worth the install?

AI-flagged interpretation of the facts above — verify before relying.

Demucs separates music into individual stems—drums, bass, vocals, and accompaniment—using a hybrid transformer-based neural network trained on waveform and spectrogram domains.

Yes. Demucs is actively maintained, has no known vulnerabilities, low install friction, and permissive licensing. It delivers state-of-the-art stem separation out of the box. Install if you need to separate music into drums, bass, vocals, or other stems; skip if you only need metadata extraction or don't work with audio.

## Install

pip install demucs
uv add demucs
poetry add demucs

## Installing demucs

Before you install: Low friction: pure Python wheel with no compiled dependencies beyond torch. Actively maintained as of July 2026 with recent updates. Requires Python 3.10+.

License in practice: MIT License permits commercial and private use with minimal restrictions; you may use, modify, and distribute Demucs freely provided you include the license notice.

Quickstart:

pip install demucs
python3 -m demucs -n htdemucs_ft path/to/song.mp3
# Outputs separated stems to ./separated/htdemucs_ft/song/

Requires Python 3.10+. torch installation may require system CUDA/GPU drivers if GPU acceleration is desired; CPU-only inference is supported but slower.

Verify before relying:

- Actual inference speed and memory requirements for typical song lengths on CPU vs. GPU hardware.
- Quality degradation or artifacts when separating non-Western music genres or atypical instrumentation.
- Whether the 6-source model (adding guitar and piano) has improved since the acknowledged piano source artifacts mentioned in the description.

## Package facts

- License: MIT License (permissive)
- Python support: supports_current
- Install friction: low
- Maintenance: active
- Downloads: 400.5K/month (top 15,000 on PyPI)
- Known vulnerabilities: none known

## Tags

music source separation, stem extraction audio, separate drums bass vocals, audio demixing neural network, waveform spectrogram separation, music decomposition model, isolate instruments from song, audio-processing, music-analysis, neural-networks

[View on SkillFed](https://skillfed.io/packages/demucs) · [View on PyPI](https://pypi.org/project/demucs/)