ElevenLabs

v1.0.0Communicationstable

Provides comprehensive access to ElevenLabs AI audio features including text-to-speech, voice cloning, sound generation, and audio isolation. Enables users to generate high-quality speech, manage voices, transform audio, and access ElevenLabs service

elevenlabselevenlabs-apimcp
Share:
1,371
Stars
0
Downloads
0
Weekly
0/5

What is ElevenLabs?

ElevenLabs is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to provides comprehensive access to elevenlabs ai audio features including text-to-speech, voice cloning, sound generation, and audio isolation. enables users to generate high-quality speech, manage voic...

Provides comprehensive access to ElevenLabs AI audio features including text-to-speech, voice cloning, sound generation, and audio isolation. Enables users to generate high-quality speech, manage voices, transform audio, and access ElevenLabs service

This server falls under the Communication category on MCPgee, the world's largest MCP server directory with 33,000+ servers.

Features

  • Provides comprehensive access to ElevenLabs AI audio feature

Use Cases

Generate high-quality speech from text using ElevenLabs AI voices.
Clone voices and create voice variants for personalized audio.
Isolate and transform audio with professional sound generation.
elevenlabs

Maintainer

LicenseMIT License
Languagepython
Versionv1.0.0
UpdatedMay 21, 2026
Statushealthy
Maintenanceactive

Works with

ClaudeOpenAIwindowsmacoslinux

Installation

Manual Installation

npx elevenlabs-mcp-server

Configuration

Configuration Details

Config File

claude_desktop_config.json

Performance

Response Metrics

Response Time< 200ms
ThroughputMedium

Resource Usage

Memory UsageLow
CPU UsageLow

How to Set Up and Use ElevenLabs

The ElevenLabs MCP Server connects AI assistants directly to ElevenLabs' suite of AI audio APIs, enabling text-to-speech synthesis, voice cloning, audio transcription, and sound generation from within any MCP-compatible client. It bridges conversational AI workflows with professional-grade audio production, so you can generate narration, clone a speaker's voice, or transcribe recordings without ever leaving your AI interface. This is the official server maintained by ElevenLabs, supporting all major audio features including voice management, speech-to-text with speaker diarisation, and data residency controls for enterprise users.

Prerequisites

  • An ElevenLabs account with an API key (free tier available at elevenlabs.io)
  • Python 3.10+ and either uv (recommended) or pip installed
  • An MCP-compatible client such as Claude Desktop, Cursor, or Windsurf
  • Sufficient ElevenLabs credits for text-to-speech and voice cloning operations
1

Install uv (recommended runtime)

ElevenLabs recommends uv as the Python runtime manager. Install it with the official installer script.

curl -LsSf https://astral.sh/uv/install.sh | sh
2

Obtain your ElevenLabs API key

Log in to elevenlabs.io, navigate to Profile Settings → API Keys, and copy your key. Keep it secure — you will pass it as an environment variable.

3

Add ElevenLabs to your MCP client configuration

Open your MCP client's config file (for Claude Desktop: ~/Library/Application Support/Claude/claude_desktop_config.json on macOS) and add the ElevenLabs server entry. The server is run via uvx which automatically resolves the package.

{
  "mcpServers": {
    "ElevenLabs": {
      "command": "uvx",
      "args": ["elevenlabs-mcp"],
      "env": {
        "ELEVENLABS_API_KEY": "<your-api-key-here>",
        "ELEVENLABS_MCP_BASE_PATH": "~/Desktop",
        "ELEVENLABS_MCP_OUTPUT_MODE": "files"
      }
    }
  }
}
4

Restart your MCP client

Fully quit and relaunch your MCP client (e.g. Claude Desktop) so it picks up the new server configuration. You should see ElevenLabs appear in the list of available tools.

5

Verify the connection

Ask your AI assistant to list available ElevenLabs voices. If the server is connected, it will return your library of voices from the API.

6

(Optional) Configure output mode and residency

Set ELEVENLABS_MCP_OUTPUT_MODE to 'resources' to receive audio as MCP resources rather than files, or 'both' for both. Enterprise users can set ELEVENLABS_API_RESIDENCY to 'eu' to pin data to European servers.

ELEVENLABS_MCP_OUTPUT_MODE=resources
ELEVENLABS_API_RESIDENCY=eu

ElevenLabs Examples

Client configuration

Complete claude_desktop_config.json entry for the ElevenLabs MCP server using uvx.

{
  "mcpServers": {
    "ElevenLabs": {
      "command": "uvx",
      "args": ["elevenlabs-mcp"],
      "env": {
        "ELEVENLABS_API_KEY": "<your-elevenlabs-api-key>",
        "ELEVENLABS_MCP_BASE_PATH": "~/Desktop",
        "ELEVENLABS_MCP_OUTPUT_MODE": "files"
      }
    }
  }
}

Prompts to try

Example prompts you can send to your AI assistant once the server is connected.

- "Generate speech from this text using the Rachel voice and save it to my desktop: 'Welcome to our product demo.'"
- "List all the voices available in my ElevenLabs account."
- "Clone a voice from the audio file at ~/Desktop/sample.mp3 and name it 'MyVoice'."
- "Transcribe the audio file at ~/Desktop/meeting.mp3 with speaker identification."
- "Convert this text to speech using a British male voice: 'The quarterly results exceeded expectations.'"
- "Generate an ambient rainstorm sound effect, 30 seconds long."

Troubleshooting ElevenLabs

Server fails to start with 'uvx: command not found'

Install uv first with 'curl -LsSf https://astral.sh/uv/install.sh | sh', then restart your terminal. Alternatively, install the package directly with 'pip install elevenlabs-mcp' and change the command in the config to 'python' with args ['-m', 'elevenlabs_mcp'].

API key errors or '401 Unauthorized' responses

Verify that ELEVENLABS_API_KEY is set correctly in the env block of your config, not as a shell environment variable. The key should start with the format provided in the ElevenLabs dashboard under Profile → API Keys.

Audio files are not appearing on the desktop

Check that ELEVENLABS_MCP_BASE_PATH points to a directory that exists and is writable. Expand the tilde manually if needed (e.g. '/Users/yourname/Desktop'). Switch to ELEVENLABS_MCP_OUTPUT_MODE=resources to receive audio inline as MCP resources instead.

Frequently Asked Questions about ElevenLabs

What is ElevenLabs?

ElevenLabs is a Model Context Protocol (MCP) server that provides comprehensive access to elevenlabs ai audio features including text-to-speech, voice cloning, sound generation, and audio isolation. enables users to generate high-quality speech, manage voices, transform audio, and access elevenlabs service It connects AI assistants to external tools and data sources through a standardized interface.

How do I install ElevenLabs?

Follow the installation instructions on the ElevenLabs GitHub repository. Clone the repo, install dependencies, and add the server config to your AI client.

Which AI clients work with ElevenLabs?

ElevenLabs works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.

Is ElevenLabs free to use?

Yes, ElevenLabs is open source and available under the MIT License license. You can use it freely in both personal and commercial projects.

Browse More Communication MCP Servers

Explore all communication servers available in the MCPgee directory. Each server includes setup guides for Claude, Cursor, and VS Code.

Quick Config Preview

{ "mcpServers": { "elevenlabs-mcp-server": { "command": "npx", "args": ["-y", "elevenlabs-mcp-server"] } } }

Add this to your claude_desktop_config.json or .cursor/mcp.json

Read the full setup guide →

Ready to use ElevenLabs?

Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.

33,000+ ServersFree & Open SourceStep-by-Step Guides