Spleeter Ai Audio Source Separation Deezer

---
name: "Spleeter AI Audio Source Separation by Deezer"
slug: "spleeter-ai-audio-source-separation-deezer"
description: "Spleeter is Deezer's open-source audio source separation library with pretrained models. It can split audio into 2, 4, or 5 stems (vocals, drums, bass, piano, accompaniment) and runs 100x faster than real-time on GPU, making it ideal for music production, remix, and audio analysis workflows."
github_stars: 28130
verification: "security_reviewed"
source: "https://github.com/deezer/spleeter"
category: "Media & Transcription"
framework: "Multi-Framework"
tool_ecosystem:
  github_repo: "deezer/spleeter"
  github_stars: 28130
---

# Spleeter AI Audio Source Separation by Deezer

Spleeter is Deezer's open-source audio source separation library with pretrained models. It can split audio into 2, 4, or 5 stems (vocals, drums, bass, piano, accompaniment) and runs 100x faster than real-time on GPU, making it ideal for music production, remix, and audio analysis workflows.

## Installation

Use the upstream install or setup path that matches your environment:
- conda install -c conda-forge ffmpeg libsndfile
- pip install spleeter
- git clone https://github.com/Deezer/spleeter && cd spleeter
- pip install poetry

Requirements and caveats from upstream:
- [![Github actions](https://github.com/deezer/spleeter/workflows/pytest/badge.svg)](https://github.com/deezer/spleeter/actions) ![PyPI - Python Version](https://img.shields.io/pypi/pyversions/spleeter) [![PyPI version]...
- written in [Python](https://www.python.org/) and uses [Tensorflow](https://tensorflow.org/). It makes it easy
- as well as directly in your own development pipeline as a [Python library](https://github.com/deezer/spleeter/wiki/4.-API-Reference#separator). It can be installed with [pip](https://github.com/deezer/spleeter/wiki/1....

Basic usage or getting-started notes:
- 2 stems and 4 stems models have [high performances](https://github.com/deezer/spleeter/wiki/Separation-Performances) on the [musdb](https://sigsep.github.io/datasets/musdb.html) dataset. **Spleeter** is also very fast...
- We designed **Spleeter** so you can use it straight from [command line](https://github.com/deezer/spleeter/wiki/2.-Getting-started#usage)
- Want to try it out but don't want to install anything ? We have set up a [Google Colab](https://colab.research.google.com/github/deezer/spleeter/blob/master/spleeter.ipynb).

- Source: https://github.com/deezer/spleeter
- Extracted from upstream docs: https://raw.githubusercontent.com/deezer/spleeter/HEAD/README.md

## Source

- [Agent Skill Exchange](https://agentskillexchange.com/skills/spleeter-ai-audio-source-separation-deezer/)