mcp-ear
This server does not currently have a deployable release on Glama. Follow the repository's setup instructions to install and configure it for your MCP client, including any required credentials and local dependencies.
mcp-ear 👂
An ear for AI assistants. Language models like Claude can talk about sound, and some can even generate it — but most can't listen. mcp-ear is an MCP server that gives Claude (or any MCP client) the ability to listen to audio files on your computer:
🗣️ Hear speech — transcribe it with a local Whisper model (90+ languages, offline, free)
🎵 Hear music — tempo, beat, pitch range, melody notes, musical key
🔊 Hear sound — loudness, dynamics, silences, frequency balance, noise vs. tone
👁️ See sound — a spectrogram image, so a vision-capable model can literally look at what it sounds like
Everything runs on your own machine. No API keys, no audio leaves your computer.
What it looks like
You: What's in
C:\recordings\voice-note.wav?Claude: (calls
listen) It's a 7-second voice note: "Hello Claude. This is a test of your new ear. The quick brown fox jumps over the lazy dog." (callsspectrogram) The speaker has a fairly low, steady voice (around 180 Hz) with three clear phrases separated by short pauses.
The spectrogram tool returns an image like this (waveform on top; time → right, pitch ↑ up, brightness = loudness; cyan line = detected pitch):

Related MCP server: media-context-mcp
Tools
Tool | What it does |
| Duration, sample rate, channels, format |
| Speech or sung lyrics → text with timestamps (optional per-word timing), auto language detection. |
| Loudness & dynamics, silences, tempo & beat steadiness, pitch range & common notes, key estimate, energy per frequency band, plain-language hints |
| The note sequence (e.g. |
| PNG image: waveform + mel spectrogram + pitch contour |
All tools take an absolute file path, and most accept start / duration (seconds) to focus on part of a long file.
Formats: WAV, FLAC, OGG and MP3 work out of the box. M4A, AAC, OPUS, WEBM and video files (MP4, MOV…) need ffmpeg on your PATH.
Install
You need Python 3.10+. The easiest way is uv, which installs and runs it in one step.
Claude Code
claude mcp add ear -- uvx --from git+https://github.com/mrtdemissek/mcp-ear mcp-earClaude Desktop
Open Settings → Developer → Edit Config and add this to claude_desktop_config.json:
{
"mcpServers": {
"ear": {
"command": "uvx",
"args": ["--from", "git+https://github.com/mrtdemissek/mcp-ear", "mcp-ear"]
}
}
}Restart Claude Desktop. Then ask it to listen to a file by its full path.
Without uv
pip install git+https://github.com/mrtdemissek/mcp-earThen use mcp-ear as the command in the configs above (no args).
First run: the dependencies are a few hundred MB, and the first
listencall downloads the Whisper model (small≈ 480 MB). After that it works offline.
Settings (environment variables)
Variable | Default | Meaning |
|
|
|
|
|
|
|
| Passed to faster-whisper |
In Claude Desktop, set them with an "env": { "MCP_EAR_WHISPER_MODEL": "medium" } block next to "args".
Honest limitations
It analyzes sound; it doesn't experience it. The plain-language hints ("speech-like", "noise-like", "steady pulse") are heuristics, and the model is told to treat them as guesses.
Sung lyrics are much harder than speech: expect misheard words, especially with the
smallmodel. In our test on a live acoustic Turkish song,mediumgot most lines right or nearly right but still misheard some words.melodyworks best on a single voice or instrument. On a full band mix you get the most prominent line, not a full transcription.Key and tempo estimates can be off by an octave (60 vs 120 BPM) or land on the relative key (C major vs A minor).
It doesn't yet recognize sound events (dog bark, doorbell, applause), separate speakers, or listen to a live microphone. See the roadmap.
Roadmap
Sound event recognition (e.g. YAMNet/PANNs: "dog barking", "glass breaking", "applause")
Speaker diarization ("who spoke when")
Live microphone listening
Compare two recordings (A/B)
PyPI release (
uvx mcp-ear)
Contributions are welcome. Open an issue or PR.
Development
git clone https://github.com/mrtdemissek/mcp-ear
cd mcp-ear
python -m venv .venv
.venv/bin/pip install -e ".[dev]" # Windows: .venv\Scripts\pip
.venv/bin/pytestThe tests synthesize sounds with known answers (an A4 note, a C major scale, a 120 BPM click track, white noise) and check that the ear hears them correctly.
How it works
Speech: faster-whisper (OpenAI Whisper on CTranslate2)
Music & signal analysis: librosa (pYIN pitch tracking, beat tracking, chroma, Krumhansl–Kessler key profiles)
Images: matplotlib
Protocol: the official MCP Python SDK (v1 and v2 both supported)
License
MIT
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
This server cannot be deployed
Maintenance
Related MCP Connectors
Audio for your agent: transcribe, speak, translate, summarise, plus sound effects and music.
Audio and video tools for your AI assistant: remove noise, enhance voices, transcribe, and more.
Audio AI tools: transcription with speakers, stems, noise removal, MIDI, speech, voices and music.
Generate AI images, videos, music, SFX & speech in any AI assistant. Results appear inline in chat.
Related MCP Servers
- FlicenseAqualityDmaintenanceEnables AI models to analyze audio files through numerical fingerprints, pitch tracking, and visual spectrograms without requiring direct audio playback. It provides tools for comparing audio iterations and detecting patterns using token-efficient analysis operations.14-
- AlicenseAqualityCmaintenanceGive your AI assistant eyes and ears — analyze any video, audio, or image, entirely on your machine.299 npm2Apache 2.0
- AlicenseNot gradedqualityDmaintenanceEnables AI agents to analyze audio files, extracting tempo, key, beat drops, volume surges, high tones, loudness, brightness, and structure, and returning structured JSON and visualizations.2MIT

jackai-stt-mcpofficial
AlicenseAqualityDmaintenanceTranscribes audio files by referencing them in chat, using OpenAI's speech-to-text models locally without uploading audio, and supports speaker diarization.125 PyPIMIT