spoken-mcp – Multilingual voice interface for Claude Desktop via…
@leszini
About spoken-mcp – Multilingual voice interface for Claude Desktop via…
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
Config
Add this server to your MCP-compatible client using the configuration below.
{
"mcpServers": {
"spoken-mcp": {
"command": "python",
"args": [
"C:\\full\\path\\to\\spoken-mcp\\tts_server.py"
]
}
}
}Tools
No tools detected
We auto-extract tools from the README. The maintainer can list them under a ## Tools heading to populate this section.
Overview
What is spoken-mcp?
spoken-mcp turns Claude Desktop into a fully voice-enabled assistant. You speak to Claude and hear responses spoken aloud in any language supported by ElevenLabs. It consists of an MCP TTS Server (for reading responses aloud via ElevenLabs Text-to-Speech) and an STT Companion (a background app that listens, transcribes via ElevenLabs Scribe v1, and pastes into Claude's input field).
How to use spoken-mcp?
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.
Key features of spoken-mcp
- 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
Use cases of spoken-mcp
- Hands-free interaction with Claude Desktop
- Voice-controlled task assistance
- Accessible computing for users with mobility impairments
- Real-time multilingual conversation via voice
FAQ from spoken-mcp
What operating systems are supported?
Windows 10 and Windows 11 are required. Other operating systems are not supported.
What dependencies are needed?
Python 3.11 or newer, an ElevenLabs API key, and the Claude Desktop application.
How does spoken-mcp handle voice input and output?
The STT companion listens to your microphone and transcribes speech using ElevenLabs Scribe v1, then pastes the text into Claude’s input field. The MCP TTS server uses the speak tool to read Claude’s responses aloud via ElevenLabs Text-to-Speech.
Is administrator access required?
No, spoken-mcp operates without requiring administrator rights.
Can I use languages other than English?
Yes, spoken-mcp works with any language supported by ElevenLabs for both transcription and speech synthesis.
Frequently asked questions
What operating systems are supported?
Windows 10 and Windows 11 are required. Other operating systems are not supported.
What dependencies are needed?
Python 3.11 or newer, an ElevenLabs API key, and the Claude Desktop application.
How does spoken-mcp handle voice input and output?
The STT companion listens to your microphone and transcribes speech using ElevenLabs Scribe v1, then pastes the text into Claude’s input field. The MCP TTS server uses the speak tool to read Claude’s responses aloud via ElevenLabs Text-to-Speech.
Is administrator access required?
No, spoken-mcp operates without requiring administrator rights.
Can I use languages other than English?
Yes, spoken-mcp works with any language supported by ElevenLabs for both transcription and speech synthesis.
Basic information
More AI & Agents MCP servers
Sphere
dtajitdinov-arisOpen marketplace where AI agents register, publish services, and transact via escrowed contracts. Live at starsphera.com.
Agentic Atlas
Avery JonesConsult field-tested agent-system design patterns through 8 hosted, read-only tools for orientation, deep reading, relationships, provenance, glossary terms, and publication decisions.
fhirHydrant
faulkjOpen-source Node.js FHIR MCP server with SMART Backend Services, metadata-aware search/CRUD tools, compact responses, FHIRPath filtering, safe pagination, audit events, and terminology lookup.
XDC AI
XDC AI is a remote MCP server available at https://xdcai.tech.
Agentery
ntlgncFree MCP for live and historical pricing for 13,000+ agents and MCPs. Never knowingly pay too much... or charge too little. Know the going rate. https://agentery.com.
Comments