# vocal-separator

> vocal-separator — zhangtt08-vocal-separator. Use this tool when you need to separate vocals from instrumentals in audio files, solving music editing and remixing challenges. The vocal-separator takes in audio files and outputs separated vocal, accompaniment, drum, and bass tracks, all through a user-friendly desktop client or Agent MCP interface. It is ideal for music producers, DJs, and audio engineers requiring high-quality, offline, and private audio separation.

Canonical page: https://skillsregistry.net/skills/zhangtt08-vocal-separator  
JSON: https://api.skillsregistry.net/v1/skills/zhangtt08-vocal-separator

## Description

🎙️ 免费好用的本地 AI 人声伴奏分离神器！基于 Meta Demucs 模型，一键离线无损提取 人声/伴奏/鼓点/贝斯，不限音频时长、零排队、100% 保护隐私，免装 Python 开箱即用，自带桌面端与 MCP 接口！

## Trust

- **Trust score (0–1):** 0.50
- **Verification tier:** unverified

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** container
- **Runtime environment:** vm
- **License:** MIT
- **Updated:** 2026-11-06

## Source

- **Source listing:** [GitHub](https://github.com/zhangtt08/vocal-separator)

## Use it

Resolve this record through the SkillsRegistry MCP server (no auth, read-only):

```
claude mcp add --transport http --scope user skillsregistry https://api.skillsregistry.net/mcp
```

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "get_skill",
    "arguments": {
      "slug": "zhangtt08-vocal-separator"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/zhangtt08-vocal-separator` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/zhangtt08-vocal-separator/pull`

---
SkillsRegistry indexes agent skills from public registries and GitHub. Skills we have analysed are scanned with Circle-IR and scored on six dimensions; each listing states its scan coverage. More: https://skillsregistry.net/llms.txt