npm package discovery and stats viewer.

Discover Tips

  • General search

    [free text search, go nuts!]

  • Package details

    pkg:[package-name]

  • User packages

    @[username]

Sponsor

Optimize Toolset

I’ve always been into building performant and accessible sites, but lately I’ve been taking it extremely seriously. So much so that I’ve been building a tool to help me optimize and monitor the sites that I build to make sure that I’m making an attempt to offer the best experience to those who visit them. If you’re into performant, accessible and SEO friendly sites, you might like it too! You can check it out at Optimize Toolset.

About

Hi, 👋, I’m Ryan Hefner  and I built this site for me, and you! The goal of this site was to provide an easy way for me to check the stats on my npm packages, both for prioritizing issues and updates, and to give me a little kick in the pants to keep up on stuff.

As I was building it, I realized that I was actually using the tool to build the tool, and figured I might as well put this out there and hopefully others will find it to be a fast and useful way to search and browse npm packages as I have.

If you’re interested in other things I’m working on, follow me on Twitter or check out the open source projects I’ve been publishing on GitHub.

I am also working on a Twitter bot for this site to tweet the most popular, newest, random packages from npm. Please follow that account now and it will start sending out packages soon–ish.

Open Software & Tools

This site wouldn’t be possible without the immense generosity and tireless efforts from the people who make contributions to the world and share their work via open source initiatives. Thank you 🙏

© 2026 – Pkg Stats / Ryan Hefner

@mcpcn/audio-source-separation-mcp

v1.0.14

Published

MCP服务器,用于火山引擎音源分离,支持人声/伴奏分离

Readme

音源分离 MCP 服务器

基于火山引擎的音源分离MCP服务器,提供人声/伴奏分离功能。

功能特性

  • 🎵 人声提取: 专门的人声分离工具,去除背景音乐
  • 🎸 伴奏提取: 专门的伴奏分离工具,去除人声
  • 🎛️ 模型选择: 标准模型和降噪增强模型
  • 📁 多格式支持: wav/mp3/aac等常见音频格式
  • 🔧 灵活配置: 可自定义输出格式和路径

工具说明

extract_vocals - 提取人声

从音频中提取人声,去除背景音乐

参数:

  • audio_path (必需): 音频文件路径
  • use_enhanced_model (可选): 是否使用降噪增强模型,默认 false
  • output_format (可选): 输出音频格式 (wav/mp3/aac),默认 wav
  • output_path (可选): 输出文件路径

示例:

{
  "audio_path": "/path/to/music.mp3",
  "use_enhanced_model": true,
  "output_format": "wav"
}

extract_accompaniment - 提取伴奏

从音频中提取伴奏,去除人声

参数:

  • audio_path (必需): 音频文件路径
  • use_enhanced_model (可选): 是否使用降噪增强模型,默认 false
  • output_format (可选): 输出音频格式 (wav/mp3/aac),默认 wav
  • output_path (可选): 输出文件路径

示例:

{
  "audio_path": "/path/to/music.mp3",
  "use_enhanced_model": false,
  "output_format": "wav"
}

模型说明

  • 标准模型 (use_enhanced_model: false)
    • 2track_vocal: 标准人声提取
    • 2track_acc: 标准伴奏提取
  • 降噪增强模型 (use_enhanced_model: true)
    • bs_4track_vocal: 降噪增强人声提取,效果更好但处理时间更长
    • bs_4track_acc: 降噪增强伴奏提取,效果更好但处理时间更长

使用限制

  • 音频时长: ≤10分钟 (建议 > 5秒)
  • 文件大小: ≤100MB
  • 仅支持音乐类音频
  • 推荐: 采样率≥44.1kHz、双声道
  • 支持格式: wav、mp3、aac、flac、m4a

安装

npm install
npm run build

配置

需要配置火山引擎API凭证环境变量:

export VOLCENGINE_ACCESS_KEY_ID="your_access_key"
export VOLCENGINE_SECRET_KEY="your_secret_key" 
export VOLCENGINE_APP_KEY="your_app_key"

启动

不建议用 npx 直接启动 MCP 服务器,因为 npx 可能向 stdout 输出提示信息,干扰 MCP 的 stdio 握手,导致「MCP 显示失败」。

推荐方式:

  • 直接运行构建后的入口:
node dist/index.js
  • 或使用包导出的可执行文件(bin):
./node_modules/.bin/audio-source-separation-mcp
  • 开发模式:
npm run dev

Claude Desktop 配置

claude_desktop_config.json 中添加:

{
  "mcpServers": {
    "audio-source-separation": {
      "command": "node",
      "args": ["/path/to/audio-source-separation-mcp/dist/index.js"],
      "env": {
        "VOLCENGINE_ACCESS_KEY_ID": "your_access_key",
        "VOLCENGINE_SECRET_KEY": "your_secret_key",
        "VOLCENGINE_APP_KEY": "your_app_key"
      }
    }
  }
}

技术架构

  • 获取key 的方法是地址是:https://www.volcengine.com/docs/6489/71995 详细查看该文档。
  • Node.js + TypeScript: 核心实现
  • 火山引擎 OpenAPI SDK: API调用和鉴权
  • MCP SDK: 符合MCP协议
  • Base64编码: 音频数据传输

License

MIT License