ElevenLabs MCP Server

ElevenLabs MCP Server

What is ElevenLabs MCP Server about?

Provides a Model Context Protocol (MCP) server that converts text to speech using the ElevenLabs API, stores job history in SQLite, and offers a sample SvelteKit client for interacting with the server.

How to use ElevenLabs MCP Server?

1. Installation – Prefer the uvx approach: no manual install needed, just configure the MCP settings JSON with the command uvx and the appropriate environment variables.
2. Running the server – The MCP client (e.g., Claude Desktop) invokes uvx elevenlabs-mcp-server based on the configuration.
3. Using the web client – Navigate to clients/web-ui, install dependencies with pnpm, copy .env.example to .env, then start the UI via pnpm dev and open http://localhost:5174.
4. Available tools – Call tools like generate_audio_simple, generate_audio_script, delete_job, list_voices, etc., through MCP.

Key features of ElevenLabs MCP Server

• Audio generation from plain text or structured scripts.
• Support for multiple voices, actors, and voice‑over parameters (stability, similarity boost, style).
• Persistent job history stored in SQLite.
• Sample SvelteKit client for text‑to‑speech conversion, script management, history playback, and audio download.
• Simple configuration via environment variables.

Use cases of ElevenLabs MCP Server

• Building voice‑over pipelines for videos, podcasts, or e‑learning content.
• Integrating real‑time speech synthesis into AI assistants or chatbots.
• Managing multi‑speaker dialogues for interactive storytelling.
• Archiving generated audio for later review or reuse.

FAQ from the ElevenLabs MCP Server

Q: Which API key is required? A: An ElevenLabs API key (ELEVENLABS_API_KEY).

Q: How to choose a voice? A: Set ELEVENLABS_VOICE_ID in the environment or use the list_voices tool to retrieve available IDs.

Q: Can I change the synthesis model? A: Yes, adjust ELEVENLABS_MODEL_ID (default eleven_flash_v2).

Q: Where are audio files saved? A: To the directory defined by ELEVENLABS_OUTPUT_DIR (default output).

Q: How is job history accessed? A: Via the get_voiceover_history tool or the resource URI voiceover://history/{job_id}.

ElevenLabs MCP Server

A Model Context Protocol (MCP) server that integrates with ElevenLabs text-to-speech API, featuring both a server component and a sample web-based MCP Client (SvelteKit) for managing voice generation tasks.

Features

• Generate audio from text using ElevenLabs API
• Support for multiple voices and script parts
• SQLite database for persistent history storage
• Sample SvelteKit MCP Client for:
  • Simple text-to-speech conversion
  • Multi-part script management
  • Voice history tracking and playback
  • Audio file downloads

Installation

Installing via Smithery

To install ElevenLabs MCP Server for Claude Desktop automatically via Smithery:

npx -y @smithery/cli install elevenlabs-mcp-server --client claude

Using uvx (recommended)

When using uvx, no specific installation is needed.

Add the following configuration to your MCP settings file (e.g., cline_mcp_settings.json for Claude Desktop):

{
  "mcpServers": {
    "elevenlabs": {
      "command": "uvx",
      "args": ["elevenlabs-mcp-server"],
      "env": {
        "ELEVENLABS_API_KEY": "your-api-key",
        "ELEVENLABS_VOICE_ID": "your-voice-id",
        "ELEVENLABS_MODEL_ID": "eleven_flash_v2",
        "ELEVENLABS_STABILITY": "0.5",
        "ELEVENLABS_SIMILARITY_BOOST": "0.75",
        "ELEVENLABS_STYLE": "0.1",
        "ELEVENLABS_OUTPUT_DIR": "output"
      }
    }
  }
}

Development Installation

1. Clone this repository
2. Install dependencies:

   uv venv
   

3. Copy .env.example to .env and fill in your ElevenLabs credentials

{
  "mcpServers": {
    "elevenlabs": {
      "command": "uv",
      "args": [
        "--directory",
        "path/to/elevenlabs-mcp-server",
        "run",
        "elevenlabs-mcp-server"
      ],
      "env": {
        "ELEVENLABS_API_KEY": "your-api-key",
        "ELEVENLABS_VOICE_ID": "your-voice-id",
        "ELEVENLABS_MODEL_ID": "eleven_flash_v2",
        "ELEVENLABS_STABILITY": "0.5",
        "ELEVENLABS_SIMILARITY_BOOST": "0.75",
        "ELEVENLABS_STYLE": "0.1",
        "ELEVENLABS_OUTPUT_DIR": "output"
      }
    }
  }
}

Using the Sample SvelteKit MCP Client

1. Navigate to the web UI directory:

   cd clients/web-ui
   

2. Install dependencies:

   pnpm install
   

3. Copy .env.example to .env and configure as needed
4. Run the web UI:

   pnpm dev
   

5. Open http://localhost:5174 in your browser

Available Tools

• generate_audio_simple: Generate audio from plain text using default voice settings
• generate_audio_script: Generate audio from a structured script with multiple voices and actors
• delete_job: Delete a job by its ID
• get_audio_file: Get the audio file by its ID
• list_voices: List all available voices
• get_voiceover_history: Get voiceover job history. Optionally specify a job ID for a specific job.

Available Resources

• voiceover://history/{job_id}: Get the audio file by its ID
• voiceover://voices: List all available voices

License

This project is licensed under the MIT License - see the LICENSE file for details.