# stemrollerapp/stemroller

Isolate vocals, drums, bass, and other instrumental stems from any song

Repository: https://github.com/stemrollerapp/stemroller
Canonical: https://ross.abutalabs.com/products/stemroller
Homepage: https://www.stemroller.com
Language: Svelte
License: NOASSERTION
License Family: other
Topics: bass, deep-learning, demucs, drums, electron, javascript, python, vocals, machine-learning, source-separation, audio-processing
Last push: 2026-06-30T04:12:28+00:00

## Health v2 (maintenance only)
Score: 84/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 90, release rhythm 66, longevity 100
- inputs: {"age_days": 1515, "days_push": 64, "days_rel": 64, "gap_med": 125, "n_releases_24m": 2}
- flags: no_license
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 3156, forks 158 (observed 2026-08-28T04:07:46.344539+00:00)

## What it is
StemRoller is a free open-source desktop app that separates vocals, drums, bass, and other stems from any song with a single click, using Facebook's Demucs deep-learning model and YouTube search integration. It is built with Electron and Svelte and bundles everything needed for stem splitting.

## Use cases
- make karaoke instrumental tracks from any song
- extract acapella vocals from a track
- split a song into vocals, drums, bass, and other stems
- create instrumental versions of songs for DJing or remixing
- download a song from YouTube and separate its stems automatically

## When to choose
- you want a simple one-click GUI for AI stem separation without using the command line
- you need free, open-source vocal/instrumental isolation for karaoke or remixing
- you want search-and-split workflow that fetches songs from YouTube for you

## When to avoid
- you need real-time or low-latency stem separation
- you need fine-grained control over the Demucs model or batch processing pipelines
- you need a supported Linux build - Linux is not officially supported
- you need more than four stems or custom separation models

## Facets
- artifact type: application
- maturity: active
- function: audio-processing, machine-learning, gui
- domain: machine-learning, media
- platform: windows, cross-platform
- tags: source-separation, demucs, stem-splitting, karaoke, acapella, yt-dlp, svelte, audio, macos, linux, electron, desktop

## Member repositories
- stemrollerapp/stemroller (main) score 84

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:07:46.344539+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 2026-08-30T07:25:38.274221+00:00, confidence not recorded.
  - readme: https://github.com/stemrollerapp/stemroller (fetched 2026-08-28T04:07:46.344539+00:00, sha 4e3f44312923)
  - homepage: https://www.stemroller.com (fetched 2026-08-29T09:40:18.424611+00:00, sha 87f082258dc1)
- Data as of 2026-08-30T08:39:29.467469+00:00.