Give your AI agents the ability to listen. Microphone capture and speech-to-text.
Give your AI agents the ability to listen. Microphone capture and speech-to-text. Exposed over MCP by the mcp mcp server, that capability becomes something an assistant can invoke while it works, not something you go and do afterwards.
The server ships on npm as mcp-listen, so your MCP client can launch it on demand — there is no separate build step. Add the server block to your client's configuration, restart it, and the tools register themselves.
Everything the assistant can do here goes through one of these:
list_audio_devices — List available microphone input devicescapture_audio — Record audio from the microphone and save as WAVvoice_query — Capture, transcribe (whisper.cpp), and query a local LLM (Ollama)You will need one environment variable: WHISPER_MODEL_PATH. Keep credentials in your client's env block or a secrets manager rather than in a file you might commit.
Supported platforms: - Windows x64 - macOS Apple silicon (arm64) - Linux x64 and arm64 (glibc) Intel Mac (darwin-x64) is not supported: Apple has discontinued the platform and no decibri binary is published for it. For list_audio_devices and capture_audio: - Node.js 18+ - A microphone For voice_query (optional): - Ollama running locally - Whisper GGML model
This sits in the AI and media services group, where several servers overlap in what they claim to do but differ sharply once you actually set them up. MCP's toolset — list_audio_devices, capture_audio, voice_query — is a fair guide to whether it matches your workflow. It is maintained by analyticsinmotion; worth a glance at recent repository activity before you build anything load-bearing on it.
We check each listing at SyncDev against the project's documentation before it goes live — if something here drifts out of date, it is a bug worth reporting.
| Tool | What it does |
|---|---|
| list_audio_devices | List available microphone input devices |
| capture_audio | Record audio from the microphone and save as WAV |
| voice_query | Capture, transcribe (whisper.cpp), and query a local LLM (Ollama) |
{
"mcpServers": {
"listen": {
"command": "npx",
"args": ["-y", "mcp-listen"],
"env": {
"WHISPER_MODEL_PATH": "your-value"
}
}
}
}Add to claude_desktop_config.json, then restart Claude Desktop.
Supported platforms: - Windows x64 - macOS Apple silicon (arm64) - Linux x64 and arm64 (glibc) Intel Mac (darwin-x64) is not supported: Apple has discontinued the platform and no decibri binary is published for it. For list_audio_devices and capture_audio: - Node.js 18+ - A microphone For voice_query (optional): - Ollama running locally - Whisper GGML model
| Variable | Description | Required |
|---|---|---|
| WHISPER_MODEL_PATH | Filesystem location the server is allowed to use. | Optional |
Build a programmable telecommunications stack for connecting telephony services with the Internet via a cloud-based utility.
Search built for AI, not humans — semantic web search that returns model-ready content, plus code context.
Answers, not links — delegate questions to Perplexity's search-grounded models and get cited responses back.
Give your assistant a voice — text-to-speech, voice cloning and audio tools from the ElevenLabs API.
Give your assistant a real code sandbox — isolated cloud VMs for actually running the code it writes.
The ML hub in your context window — search models, datasets, papers and run Spaces from the official server.