Provides comprehensive access to ElevenLabs API features including text-to-speech conversion, voice management, speech-to-speech transformation, sound effect generation, audio isolation for noise removal, and user account management with history tracking.
ElevenLabs MCP Server
A comprehensive Model Context Protocol (MCP) server for the ElevenLabs API, providing access to all major ElevenLabs features including text-to-speech, voice generation, audio isolation, and more.
Features
This MCP server provides tools for:
Text to Speech
text-to-speech: Convert text to speech with customizable voice settings
text-to-speech-streaming: Stream text-to-speech audio in real-time
Voice Management
get-voices: List all available voices with search and filtering
get-voice: Get detailed information about a specific voice
get-models: List all available AI models
Audio Transformation
speech-to-speech: Transform audio from one voice to another (voice changer)
sound-generation: Create sound effects from text descriptions
audio-isolation: Remove background noise from audio
History & User Management
get-history: Get history of all generated audio
get-history-item: Get a specific history item by ID
get-history-item-audio: Download audio from a history item
delete-history-item: Delete a history item
get-user: Get current user information
get-subscription: Get user subscription details
Installation
Configuration
The server requires an ElevenLabs API key. You can configure this when connecting the server to your MCP client.
Configuration Schema
Usage with Smithery
Development
This will start the server in development mode with hot reloading.
Build
Deploy to Smithery
Push your code to GitHub
Go to Smithery
Click "Deploy" and connect your GitHub repository
Usage with Claude Desktop or Cursor
Add this to your MCP settings:
API Key
Get your ElevenLabs API key from ElevenLabs Settings.
Example Usage
Generate Speech
List Available Voices
Create Sound Effect
Remove Background Noise
API Reference
All tools follow the ElevenLabs API documentation.
Audio Format
Audio files are returned as base64-encoded strings. Supported formats include:
MP3 (various bitrates)
PCM (various sample rates)
μ-law format (for Twilio)
Development
The server is built using:
@modelcontextprotocol/sdk - MCP SDK
@smithery/sdk - Smithery SDK
zod - Schema validation
License
MIT
Resources
This server cannot be installed
remote-capable server
The server can be hosted and run remotely because it primarily relies on remote services or has no dependency on the local environment.
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 services through natural language interactions.