ElevenLabs

by ElevenLabs

v0.11.0

Repository Docs

Featured Developer Tools

voicetext-to-speechaudiotranscription

Summary

ElevenLabs' official MCP server — generate speech, clone voices, transcribe audio, and build voice agents.

Features

Generate speech in hundreds of voices and languages
Clone voices and design new ones from a description
Transcribe audio and isolate voices from noise

Installation

Set up this MCP server in your favorite AI agent — copy a ready-made configuration below.

Any MCP-compatible agent

Most agents (Claude, Cursor, Windsurf, VS Code, and more) read a standard mcpServers configuration.

Open your agent's MCP configuration file.
Merge the snippet below into it, filling in the environment variables with your own values.
Restart the agent — the "ElevenLabs" tools will be available.

{
  "mcpServers": {
    "elevenlabs": {
      "command": "uvx",
      "args": [
        "elevenlabs-mcp"
      ],
      "env": {
        "ELEVENLABS_API_KEY": "your-api-key"
      }
    }
  }
}

Claude Code

Add the server with a single CLI command.

claude mcp add elevenlabs -e ELEVENLABS_API_KEY=your-api-key -- uvx elevenlabs-mcp

Claude Desktop

Add the server to claude_desktop_config.json (Settings → Developer → Edit Config).

{
  "mcpServers": {
    "elevenlabs": {
      "command": "uvx",
      "args": [
        "elevenlabs-mcp"
      ],
      "env": {
        "ELEVENLABS_API_KEY": "your-api-key"
      }
    }
  }
}

Cursor

{
  "command": "uvx",
  "args": [
    "elevenlabs-mcp"
  ],
  "env": {
    "ELEVENLABS_API_KEY": "your-api-key"
  }
}

Windsurf

{
  "command": "uvx",
  "args": [
    "elevenlabs-mcp"
  ],
  "env": {
    "ELEVENLABS_API_KEY": "your-api-key"
  }
}

VS Code

{
  "command": "uvx",
  "args": [
    "elevenlabs-mcp"
  ],
  "env": {
    "ELEVENLABS_API_KEY": "your-api-key"
  }
}

Description

ElevenLabs' official MCP server puts its entire audio platform behind tools an assistant can call, so producing narration becomes part of a conversation rather than a separate application.

What it covers

Text to speech across a large voice library and many languages, with control over stability and style
Voice cloning from an audio sample, and voice design from a text description of how a voice should sound
Speech to text transcription with speaker diarisation
Audio isolation for stripping background noise from a recording
Sound effects generated from a description
Conversational agents — create and configure voice agents, and initiate outbound calls
Voice library search for finding a voice matching a description

Practical uses

Narrating a script the assistant just wrote, producing a localised version of a video's audio, transcribing a recording and then acting on the transcript, and prototyping voice agents without writing integration code.

Requires an ElevenLabs API key; runs with uvx elevenlabs-mcp. Generated audio is written to a configurable output directory.