[!WARNING] This MCP app is deprecated in favor of the ElevenLabs hosted MCP server.

The hosted server is available at https://api.elevenlabs.io/v1/mcp, with nothing to install or run locally. It authenticates with OAuth, so no API keys are copied into your client. See the hosted MCP server documentation to connect from Claude, Cursor, or any other MCP client.

This repository is no longer actively maintained.

Audio Player MCP Bundle for Claude Desktop with ElevenLabs integration. Generate speech, sound effects, and music, or play any local audio file.

Features

• Text-to-Speech - Generate speech from text using ElevenLabs voices
• Sound Effects - Create sound effects from text descriptions
• Music Generation - Compose music from prompts
• Audio Playback - Play any local audio file with a built-in player UI
• Playlist Support - Queue multiple tracks with playlist view
• Playback Controls - Progress bar, speed adjustment, and standard controls

Installation

Build the MCPB Bundle

# Clone the repository
git clone https://github.com/elevenlabs/elevenlabs-mcp-player.git
cd elevenlabs-mcp-player

# Install dependencies
npm install

# Build and pack the bundle
npm run pack

This creates elevenlabs-player.mcpb in the project root.

Install in Claude Desktop

Open the bundle with Claude Desktop:

open elevenlabs-player.mcpb

Or double-click the .mcpb file in Finder.

Configuration

To use the ElevenLabs generation features (TTS, sound effects, music), configure your API key in Claude Desktop:

1. Open Claude Desktop settings
2. Navigate to the ElevenLabs Player extension settings
3. Enter your ELEVENLABS_API_KEY

Usage

Generate Speech

"Say 'Hello, world!' using ElevenLabs"

"Generate speech for this text: Welcome to the future of AI"

Generate Sound Effects

"Create a sound effect of thunder and rain"

"Generate the sound of a spaceship taking off"

Generate Music

"Compose a calm piano melody for relaxation"

"Generate upbeat electronic music for a workout"

Play Local Audio

"Play the audio file at /Users/me/Music/song.mp3"

"Play these audio files: /path/to/track1.mp3 and /path/to/track2.mp3"

Tools

generate_tts

Generates speech from text using ElevenLabs text-to-speech.

generate_sound_effect

Generates a sound effect from a text description.

generate_music

Generates music from a text prompt.

play_audio

Plays one or more local audio files.

Supported Audio Formats

• MP3 (.mp3)
• WAV (.wav)
• OGG (.ogg)
• M4A (.m4a)
• AAC (.aac)

Development

Requirements

• Node.js 20+
• npm

Testing Locally

Use the MCP Inspector to test the server without Claude Desktop:

# Install dependencies
npm install

# Build and run with MCP Inspector
npm run dev

This opens a browser UI at http://localhost:6274 where you can:

• View available tools
• Test tool calls with sample inputs
• Inspect responses and debug issues

Scripts

Project Structure

├── manifest.json          # MCPB bundle manifest
├── server.ts              # MCP server with tool registration
├── src/
│   ├── mcp-app.tsx        # React audio player UI
│   └── components/ui/     # UI components
├── dist/
│   ├── server.js          # Compiled server
│   └── mcp-app.html       # Bundled UI
└── .mcpbignore            # Files to exclude from bundle

Privacy

This extension runs locally on your machine. Local audio files are read from your filesystem and are not transmitted externally.

When using ElevenLabs generation features (TTS, sound effects, music), your text prompts are sent to the ElevenLabs API. Generated audio is saved locally to your configured output directory.

For more information about ElevenLabs' data practices, see the ElevenLabs Privacy Policy.

License

MIT License - see LICENSE for details.