# VocalSplit

Remove vocals from a song with your AI agent: an instrumental karaoke track and an a cappella vocal, or drums, bass and other stems, separated by the Demucs model on your own computer, with practice mixes, key changes and an offline mixer to compare every part.

Canonical page: https://skillrove.dev/skills/vocalsplit
Version: 1.0.0
Package price: USD 4.99 per individual package
Installation hosts: Codex, Claude Code, Cursor
Output: Instrumental, vocals, stems and custom mixes with a mixer to compare them

## What it does

- Separates songs with the Demucs model on your own computer into an instrumental and an a cappella, or into drums, bass, other, guitar and piano stems, from MP3, WAV, FLAC, M4A or video.
- Makes practice mixes with a quiet guide vocal and karaoke versions in another key, keeps every file adding back up to the original, and lowers all files together if one would clip.
- Measures loudness and peaks, finds where the vocals are, and builds an offline mixer page with every part in sync, mute, solo, levels and A/B.

Best suited to: Singers, karaoke hosts, musicians practising, DJs and producers, and video makers working with their own or licensed music.

Scope limits: Separation is an estimate: expect faint vocal traces and some band in the vocal, especially from MP3s. Needs PyTorch and Demucs installed; it does not clear rights to commercial recordings.

## Documented deliverables and requirements

- instrumental: the karaoke track
- vocals: the a cappella
- stems/: drums, bass, other (guitar and piano with htdemucs_6s)
- mixes/: practice mixes and key changes
- index.html: offline mixer with mute, solo, levels and A/B
- report.md with loudness, peaks and where the vocals are

Runtime requirements: Python 3.9+ · PyTorch and Demucs · FFmpeg · runs locally, no API key

Working example: https://skillrove.dev/skillrove/samples/vocalsplit/v1.0.0/index.html

The demo song is original, made with a synthesized band and FFmpeg's flite voice. Separation is an estimate; use it only on recordings you have the rights to.

## Questions before installation

### How do I get VocalSplit?

The listed individual package price is USD 4.99. Premium downloads require a confirmed purchase or active membership. Your agent subscription, model access and external provider credits are separate.

- [Compare access and pricing](https://skillrove.dev/pricing)

### Which agents can use this skill?

This release lists Codex, Claude Code, Cursor as intended installation hosts. Check the package’s dependencies and permissions before running it. These labels do not certify that every workflow has been tested in every agent.

- [Codex setup](https://skillrove.dev/skills/agent/codex)
- [Claude Code setup](https://skillrove.dev/skills/agent/claude-code)
- [Cursor setup](https://skillrove.dev/skills/agent/cursor)

### What files can this workflow generate?

The documented 1.0.0 workflow lists: instrumental: the karaoke track; vocals: the a cappella; stems/: drums, bass, other (guitar and piano with htdemucs_6s); mixes/: practice mixes and key changes; index.html: offline mixer with mute, solo, levels and A/B; report.md with loudness, peaks and where the vocals are. Some files or exports are optional; follow the package’s setup and inspect the delivered result.

- [Review all deliverables](https://skillrove.dev/skills/vocalsplit#skill-what-you-get)
- [Inspect the working example](https://skillrove.dev/skillrove/samples/vocalsplit/v1.0.0/index.html)

### What should I check before using the result?

The demo song is original, made with a synthesized band and FFmpeg's flite voice. Separation is an estimate; use it only on recordings you have the rights to.

- [Read the installation guide](https://skillrove.dev/guides/how-to-install-a-claude-skill)
- [Review third-party notices](https://skillrove.dev/third-party-notices)

## Source and access

These facts come from the public Skillrove catalog and the documented active release. Agent labels describe intended installation hosts, not certification across every model. Package licenses apply; model accounts, provider credits and credentials are separate. Public facts do not grant download access.

[Installation guide](https://skillrove.dev/install/agent.md) · [Support](https://skillrove.dev/contact)
