---
title: "audio-stemming"
description: "Deterministic vocal and instrumental audio stem separation using Meta HTDemucs."
canonical: https://agentpluginsdirectory.com/plugins/audio-stemming
last-updated: 2026-11-07
---

# audio-stemming
Deterministic vocal and instrumental audio stem separation using Meta HTDemucs.
- Slug: audio-stemming
- Publisher: G. H. Chinoy
- Repository: https://github.com/ghchinoy/audio-tools-for-agents
- Manifest: plugins/audio-stemming/plugin.json
- Version: 0.1.0
- License: Apache-2.0
- Category (editorial): creative-media
- Skills: 1 (audio-stemming)
- MCP servers: 0
- Stars: 1
- Repository created: 2026-09-04
- Repository last pushed: 2026-10-23
- Publisher type: User
- Listing: https://agentpluginsdirectory.com/plugins/audio-stemming
- Schema: https://agent-plugins.org/schemas/1.0.0/plugin.schema.json

## Skills

- audio-stemming: Separate mixed audio tracks into isolated vocal and instrumental stems (vocals, drums, bass, guitar, piano, other) using local HTDemucs PyTorch inference. Use when an agent needs to isolate vocals, strip drums or accompaniment, or extract multitrack stems from WAV or MP3 files.

Descriptions come from the frontmatter of each SKILL.md, punctuation lightly normalized.