elevenlabs-mcp

MCP.Pizza Chef: elevenlabs

The official ElevenLabs connection lets your assistant speak text aloud in a chosen voice, transcribe recordings into text with speakers labelled, clone a voice from a sample, design a brand new one from a description, and build sound effects or a whole soundscape. Finished files are saved to a folder you pick, by default your Desktop. You need a free ElevenLabs account key, and the free tier includes a monthly allowance of credits. It works in Claude Desktop, Cursor, and Windsurf.

Other
Writing

Use This MCP server To

Turn a blog post into a narrated audio file Transcribe an interview and label who said what Create a voice for a character I am writing Make sound effects for a short video Convert my own recording into a different voice

README

export

Discord Community Twitter PyPI Tests

Official ElevenLabs Model Context Protocol (MCP) server that enables interaction with powerful Text to Speech and audio processing APIs. This server allows MCP clients like Claude Desktop, Cursor, Windsurf, OpenAI Agents and others to generate speech, clone voices, transcribe audio, and more.

Quickstart with Claude Desktop

  1. Get your API key from ElevenLabs. There is a free tier with 10k credits per month.
  2. Install uv (Python package manager), install with curl -LsSf https://astral.sh/uv/install.sh | sh or see the uv repo for additional install methods.
  3. Go to Claude > Settings > Developer > Edit Config > claude_desktop_config.json to include the following:
{
  "mcpServers": {
    "ElevenLabs": {
      "command": "uvx",
      "args": ["elevenlabs-mcp"],
      "env": {
        "ELEVENLABS_API_KEY": "<insert-your-api-key-here>"
      }
    }
  }
}

If you're using Windows, you will have to enable "Developer Mode" in Claude Desktop to use the MCP server. Click "Help" in the hamburger menu at the top left and select "Enable Developer Mode".

elevenlabs-mcp FAQ

Does it need a key?
Yes, an ElevenLabs key from your account settings; the free tier comes with a monthly credit allowance.
Can I use this to narrate an article I wrote?
Yes — hand it the text, pick a voice, and it saves a finished audio file.
Where do the files end up?
In a folder you choose, or your Desktop by default; that folder also limits which files it may read.
Which apps does it work in?
Claude Desktop, Cursor, and Windsurf are documented, and other MCP clients work too.
Does it cost money to run?
Each request uses ElevenLabs credits, so heavy use will go beyond the free monthly allowance.
Why do some requests time out?
Voice design and audio clean-up can take a while, so long jobs sometimes need a second attempt.