spoken-mcp – Multilingual voice interface for Claude Desktop via ElevenLabs
LocalAbout spoken-mcp – Multilingual voice interface for Claude Desktop via ElevenLabs
spoken-mcp adds voice interaction to Claude Desktop: an MCP TTS server reads replies aloud via ElevenLabs, while a companion app transcribes speech into Claude's input. It is intended for users who want hands-free or spoken interaction.
Key features
- 01Converts replies to speech via ElevenLabs
- 02Transcribes and pastes microphone input
- 03Push-to-talk and two VAD modes
- 04System tray status for listening and recording
Use cases
- 01Ask questions and hear replies hands-free
- 02Choose a preferred voice input mode
- 03Automatically send or review transcriptions
MCP support
The MCP TTS server exposes a speak tool to Claude Desktop, sending reply text to ElevenLabs for audio generation and playback.
Configuration
Local server config is the same for every client. Copy it into your client’s MCP config file.
We haven’t collected a package or remote endpoint for this server. Follow the instructions in the project README.
Tools
Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.
Details
The maintainer has not added details yet. Check the README in the repository.
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.