mcp-elevenlabs
Fork of ElevenLabs MCP server with enhanced conversational AI features
claude mcp add --transport stdio 199-mcp-mcp-elevenlabs npx elevenlabs-mcp-enhanced \ --env ELEVENLABS_API_KEY="<insert-your-api-key-here>"
How to use
This MCP server is an enhanced ElevenLabs integration that enables Claude Desktop and other MCP clients to interact with ElevenLabs' Text-to-Speech and conversational AI capabilities. It supports official ElevenLabs v3 model interactions, multi-speaker dialogues, and tools for retrieving conversation history and transcripts. You can use it to generate speech, clone voices, transcribe audio, and manage conversations, with features like conversation history retrieval, transcript formats (plain, timestamps, JSON), and real-time monitoring of ongoing conversations. The server is designed to be used via npx or a globally installed npm package, allowing seamless integration into MCP clients and workflows.
To run locally, you’ll typically use npx elevenlabs-mcp-enhanced with your ElevenLabs API key provided through the ELEVENLABS_API_KEY environment variable. This setup makes it easy to leverage the enhanced toolset without a full local install, and it supports both single-speaker and multi-speaker dialogue scenarios, automatic dialogue formatting improvements, and robust error guidance to help AI agents succeed.
How to install
Prerequisites:
- Node.js 16+ (for npm/npx) — ensure it is installed and available in your PATH
- npm (comes with Node.js) or yarn if preferred
- An ElevenLabs API Key (create one at https://elevenlabs.io/app/settings/api-keys)
Installation options:
Option A: Zero install (recommended – use via npx)
- No installation required. Simply run:
npx elevenlabs-mcp-enhanced --api-key YOUR_API_KEY
Option B: Global install (one-time install, then run anywhere)
- Install globally:
npm install -g elevenlabs-mcp-enhanced
- Run with your API key:
elevenlabs-mcp-enhanced --api-key YOUR_API_KEY
Option C: Environment variable (recommended for local development)
- Set the API key in your environment and run via npx:
export ELEVENLABS_API_KEY="your-api-key"
npx elevenlabs-mcp-enhanced
Notes:
- The server relies on the ELEVENLABS_API_KEY environment variable or the --api-key flag to authenticate with ElevenLabs.
- The MCP enables integration across clients like Claude Desktop, Cursor, Windsurf, and others via the MCP protocol.
Additional notes
Tips and troubleshooting:
- Ensure your ELEVENLABS_API_KEY is valid and has permissions for the requested operations.
- When using multi-speaker dialogues, prefer model="v3" configurations to take advantage of the official ElevenLabs v3 model features.
- If you encounter rate limits or timeouts on long dialogues, enable dynamic timeouts or chunk dialogues into smaller segments as described by the v3 workflow.
- For transcripts, you can retrieve formats in plain text, with timestamps, or JSON for programmatic processing.
- Windows users may need to enable Developer Mode in Claude Desktop to allow MCP server integration via configuration files.
- Check that Node.js version matches the requirements and that your environment variable is accessible to the process running the MCP server.
Related MCP Servers
web-agent-protocol
🌐Web Agent Protocol (WAP) - Record and replay user interactions in the browser with MCP support
mcp-python-interpreter
MCP Python Interpreter: run python code. Python-mcp-server, mcp-python-server, Code Executor
oxylabs
Official Oxylabs MCP integration
mcp-zen
Enhanced Zen MCP Server with 'zen' default tool and improvements
rlm-claude
Recursive Language Models for Claude Code - Infinite memory solution inspired by MIT CSAIL paper
mcp-limitless
Advanced MCP Server with AI-powered Limitless API features: natural time queries, meeting detection, action item extraction, daily summaries, and speaker analytics