About Voice-Enabled MCP Server
Voice-Enabled MCP Server connects Claude AI with ElevenLabs to support voice-based conversations. It is for Claude Desktop users and provides 19 ElevenLabs MCP tools, with responses spoken in a selected voice.
Key features
- 01Claude Desktop integration
- 0219 ElevenLabs MCP tools
- 03Voice selection by ID
- 04Spoken AI responses
Use cases
- 01Having voice conversations with Claude
- 02Choosing a voice for spoken responses
MCP support
The server integrates with Claude Desktop and makes 19 ElevenLabs tools available through MCP.
Configuration
Local server config is the same for every client. Copy it into your client’s MCP config file.
Tools
Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.
Details
From the project READMEVoice-Enabled MCP Server
An MCP server connecting Claude AI with ElevenLabs for voice enabled conversation capabilities.
Quick Setup
Prerequisites
- Claude Desktop
- ElevenLabs API key
- Python 3.8+
Installation
- Install
uvpackage manager:
curl -LsSf https://astral.sh/uv/install.sh | sh
- Install the MCP server:
uv pip install elevenlabs-mcp
- Configure Claude Desktop:
- Go to Settings > Developer > Edit Config
- Add to
claude_desktop_config.json:
{
"mcpServers": {
"ElevenLabs": {
"command": "uvx",
"args": ["elevenlabs-mcp"],
"env": {
"ELEVENLABS_API_KEY": "YOUR_API_KEY"
}
}
}
}
Windows users: Enable Developer Mode via Help > Enable Developer Mode
Usage
- Launch Claude Desktop
- After successful integration, you'll see a developer sign indicating 19 available ElevenLabs MCP tools
- Start a voice conversation with ElevenLabs by stating your preferred voice ID
- The AI will now respond to your queries using the selected ElevenLabs voice, powered by Claude's intelligence
- You can have natural voice conversations, asking questions and receiving spoken responses
Demo and Next Steps
Comments
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.