mcp-listen — Claude Code MCP server: mic capture and speech-to-text
Lets an agent reach the microphone: list input devices, record a WAV file, transcribe speech on the same machine and hand the text to Ollama.
claude mcp add mcp-listen -- npx -y mcp-listenWhat mcp-listen does
Three tools come with the server. list_audio_devices returns the available microphones as JSON, capture_audio writes a recording to a WAV file, and voice_query runs the whole chain: record, transcribe locally with whisper.cpp, then query the Ollama daemon on the same host. The audio never leaves the machine.
Recording can end on its own. With stop_on_silence: true the bundled Silero VAD watches for voice activity, so nothing extra is downloaded. Arguments are checked before any recording starts; a parameter the tool does not declare comes back as an error naming it, and a rejected call writes nothing to disk. Node.js 18+ and a microphone cover list_audio_devices and capture_audio.
Intel Macs are out: Apple discontinued that platform and no decibri binary ships for it. Windows x64, Apple silicon macOS and Linux on x64 or arm64 are the supported targets. voice_query additionally expects Ollama already running plus a Whisper GGML model — without both, that one tool stays quiet while device listing and plain capture keep working.
What it helps with
- record a voice note without leaving the agent session
- pick the right microphone when the machine has several
- let the recording stop by itself once the speaker finishes
- transcribe speech locally instead of shipping audio to a cloud API
- route a spoken question through a local Ollama model
Example prompts for the agent
- List the available microphones
- Record 5 seconds from the microphone and save it as WAV
- Record my question, transcribe it and send it to Ollama
How to install mcp-listen
Platform CLI
claude mcp add mcp-listen -- npx -y mcp-listenPlatform CLI
codex mcp add mcp-listen -- npx -y mcp-listenConfig file
{
"mcpServers": {
"mcp-listen": {
"command": "npx",
"args": [
"-y",
"mcp-listen"
]
}
}
}Config file
{
"servers": {
"mcp-listen": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"mcp-listen"
]
}
}
}Platform CLI
gemini mcp add mcp-listen npx -y mcp-listenStep by step, with commands for each platform: How to add an MCP server to Claude Code, Codex, Cursor, VS Code, Gemini CLI and more
Questions about mcp-listen
How do I install mcp-listen in Claude Code?
Run claude mcp add mcp-listen -- npx -y mcp-listen.
What does mcp-listen do?
It exposes three tools to the agent: device listing, WAV capture, and a voice query that transcribes with whisper.cpp and asks Ollama for an answer.
What does voice_query need to work?
A local Ollama daemon and a Whisper GGML model. Capture and device listing work without either.
