Audacitymcp

Name: Audacitymcp
Author: xDarkzx

@xDarkzx

关于 Audacitymcp

AudacityMCP connects any MCP-compatible AI assistant to [Audacity](https://www.audacityteam.org/), giving it full control over audio editing through 131 tools and 9 pipelines spanning effects, cleanup, mastering, and more. Talk to your AI assistant and it edits your audio in real

#audacity #mcp-server #audio-processing #audio-editing #mastering #transcription #python #mod-script-pipe #anthropic

基本信息

分类

其他

许可证

Apache-2.0

运行时

python

传输方式

stdio

发布者

xDarkzx

提交者

Dan

配置

使用下面的配置,将此服务器添加到你的 MCP 客户端。

{
  "mcpServers": {
    "audacity": {
      "command": "audacity-mcp"
    }
  }
}

工具

未检测到工具

工具是从 README 中自动提取的。维护者可以在 ## Tools 标题下列出工具,即可填充这部分内容。

概览

What is AudacityMCP?

AudacityMCP connects any MCP-compatible AI assistant to Audacity, giving it full control over audio editing through 131 tools covering effects, cleanup, mastering, transcription, and more. Everything runs locally through Audacity's named pipe interface—no cloud, no API keys for audio processing. Works with Audacity 3.x only.

How to use AudacityMCP?

Download or clone the repository, then run the installer (install.bat on Windows, bash install.sh on macOS/Linux) to install audacity-mcp from PyPI, enable mod-script-pipe, and configure Claude Desktop automatically. For other MCP clients, install manually with pip install audacity-mcp and add to your client's MCP config. Audacity must be open first.

Key features of AudacityMCP

131 tools across 11 categories (effects, editing, cleanup, mastering, transcription, etc.)
9 one-click pipelines for common audio tasks (podcast, music mastering, interview, etc.)
Local transcription via faster-whisper—audio never leaves your machine
Works with any MCP-compatible client (Claude Desktop, Claude Code, Cursor, etc.)
Pipelines are safe—they only reduce peaks, never boost loudness

Use cases of AudacityMCP

Podcasters wanting consistent professional sound without audio engineering knowledge
Musicians needing quick genre-tuned mastering
Content creators cleaning up interviews, voiceovers, or field recordings
Anyone who prefers describing audio edits in plain English over clicking through menus

FAQ from AudacityMCP

Which Audacity versions are supported?

AudacityMCP currently works with Audacity 3.x only. Audacity 4.x is not yet supported.

Does AudacityMCP send my audio to the cloud?

No. All audio processing runs locally through Audacity's named pipe interface. No cloud, no API keys are needed for audio processing.

How do pipelines handle loudness?

Pipelines only reduce peaks if they are too hot; they never boost loudness. After a pipeline, you can ask the AI to run loudness_normalize to hit a specific LUFS target (e.g., -14 for Spotify).

How do I set up local transcription?

Local transcription is experimental and requires separate setup. Powered by faster-whisper, it runs entirely offline with 5 model sizes and supports multiple export formats (SRT, VTT, TXT). See the installation guide for detailed setup.