OpenViSTAI · Agents · Blockchain · Crypto
Submit a project
Menu
Audio & Voice AI

Stemroller

Stemroller is a desktop application that uses Demucs to separate songs into vocal and instrumental audio stems, with YouTube search results integrated into its song-finding workflow.

Explore the practical guide ↓

Independent OpenViST project profile, based on linked sources.

Stemroller — OpenViST project profile in Audio & Voice AI.
OpenViST project illustration. See the linked sources for product details.
Understand the project

Practical overview

When it fits

Use Stemroller when you want a desktop workflow that starts with searching for a song and produces separated audio stems. Allow several minutes for a split to complete.

Who it is for

  • People who want to isolate vocals from a song.
  • Musicians, remixers, or audio hobbyists who want access to separate instrumental parts such as drums and bass.
  • Developers interested in working with the project's Svelte-based desktop application.

Documented uses

  • Find a song by title or artist through integrated YouTube search results.
  • Run source separation on a selected song.
  • Open the extracted vocal and instrumental stems from the app.
Before you choose

Requirements & limits

The README provides download paths through the Stemroller website and GitHub releases, and describes bundles for Windows and macOS. Linux is not officially supported.

  • Demucs is the documented source-separation algorithm.
  • The song search uses integrated YouTube results.
  • The README says splitting takes several minutes.
  • The ready-to-use download bundle is documented for Windows and macOS; Linux setup requires separately installed dependencies and is not officially supported. The project is written in Svelte.

Check current requirements in the official documentation. Source-based guidance does not mean OpenViST has run or independently tested this project.

Source-based practical guide

Download Stemroller for desktop use

Obtain the app bundle intended for splitting songs.

Before you start

  • A Windows or macOS desktop.
  • Access to the Stemroller website or GitHub releases page.

Steps

  1. Open the Stemroller website or the project's GitHub releases page.

  2. Download the latest version for the desktop platform.

Expected outcome

The project says the downloaded bundle includes everything needed to split stems.

Guide limitations

  • The README labels Linux as not officially supported.
  • This guide covers obtaining the bundle, not running a separation task.
Documentation 1 ↗
Source-based practical guide

Set up Stemroller for Linux development

Install the documented dependencies and start the development app on Linux.

Before you start

  • Linux environment.
  • Git, Node.js/npm, and Python package installation tools.

Steps

  1. Clone the repository and change into its directory.

  2. Install project dependencies with the command below.

    Documented command
    npm i -D

  3. Install ffmpeg globally, and install demucs and yt-dlp globally with pip.

  4. If an “Couldn't find appropriate backend” error occurs, try installing libsox-dev.

  5. Start development mode with the command below.

    Documented command
    npm run dev

Expected outcome

The documented development command starts Stemroller in development mode, once dependencies are in place.

Guide limitations

  • Linux is explicitly described as not officially supported.
  • The README notes libsox-dev only as a possible remedy for a backend error.
Documentation 1 ↗
Evidence and transparency

Sources & review

Official repository ↗
Source record details
Source availability
Active
Sources checked
17 October 2026
Original website title
stemrollerapp/stemroller · Official homepage title · retained in its source language
How we review sourcesSuggest a correction