spoken-mcp – Multilingual voice interface for Claude Desktop via ElevenLabs
About
Spoken-mcp is a voice interface for the Claude Desktop app. It consists of two components: an MCP TTS server that lets Claude speak responses aloud via ElevenLabs, and an STT companion app that transcribes your speech and pastes it into Claude's input field. Supports three input
Details
- Author
- leszini
- Downloads
- 588
- Categories
- AI
Jump to
- Speak tool for ElevenLabs Text-to-Speech (MP3, 44.1 kHz)
- STT companion using ElevenLabs Scribe v1 transcription
- Three input modes: push-to-talk, VAD, always-on
- System tray icon with state indicators
- No administrator rights required
- Multilingual support via ElevenLabs
Setting up with Highlight
This MCP is not yet compatible with Highlight’s one-click setup. However, you can still use it with Highlight by following these steps:
- Download and install Highlight from highlightai.com/download
- Navigate to the plugins tab and select "Add Custom Plugin"
-
Configure the plugin with the settings below
Plugin Name
spoken-mcp – Multilingual voice interface for Claude Desktop via ElevenLabsCommand (node, npx, python, etc.)Please refer to the README for specific instructions on how to obtain API keys or other required environment variables.
- Enable "Start Automatically" if you want the plugin to start when Highlight launches
From the repository
Install spoken-mcp on Windows 10/11 with Python 3.11+ and obtain an ElevenLabs API key. Run the MCP TTS server and STT companion, then choose one of three input modes: push-to-talk, VAD toggle, or always-on voice detection. A system tray icon shows the current state (idle/listening/recording). Full setup instructions are at the project’s GitHub repository.
Claude Desktop / Cursor
Paste into your MCP client config file to install this server.
{
"mcpServers": {
"spoken-mcp \u2013 multilingual voice interface for claude desktop via elevenlabs": {
"spoken-mcp": {
"command": "python",
"args": [
"C:\\full\\path\\to\\spoken-mcp\\tts_server.py"
]
}
}
}
}McpServers
{
"spoken-mcp": {
"command": "python",
"args": [
"C:\\full\\path\\to\\spoken-mcp\\tts_server.py"
]
}
}spoken-mcp turns Claude Desktop into a fully voice-enabled assistant. Speak to Claude and hear responses spoken aloud — in any language supported by ElevenLabs.
The system consists of two components:
MCP TTS Server: Claude calls the speak tool to read responses aloud via ElevenLabs Text-to-Speech (MP3, 44.1 kHz)
STT Companion: A background app that listens to your microphone, transcribes via ElevenLabs Scribe v1, and pastes into Claude's input field
Three input modes: push-to-talk, VAD toggle, and always-on voice detection. System tray icon shows current state (idle/listening/recording). No admin rights required.
Requirements: Windows 10/11, Python 3.11+, ElevenLabs API key, Claude Desktop app.
Full setup guide and documentation: https://github.com/leszini/spoken-mcp
Sign in to leave a review
Use Google, GitHub, or an email account so ratings stay tied to real people.
No reviews posted yet.
