MCP server · Health and learning

Voice Coach MCP server

Let your AI listen to your singing or speaking and give you real coaching on pitch, pronunciation and pacing.

Health and learning Music For education Education

This is a helper that gives your AI ears. It records from your microphone, measures what it hears on your own computer, and then your AI turns those numbers into friendly coaching. It is made for anyone practicing singing, English pronunciation or public speaking.

What is an MCP server? The 30-second version

On its own, your AI can only chat with you. It cannot hear anything, so it cannot tell if you sing in tune or mumble. An MCP server is a small helper program that adds a new skill to your AI, and this one connects it to your microphone. When you ask for help with your voice, your AI calls this helper, the helper records and measures your audio locally, and your AI talks to you about what it found.

What this MCP server does

You tell your AI what you want to practice, like singing a scale in tune or reading a sentence out loud. Your AI asks this helper to record your microphone for a few seconds. The helper saves the recording on your computer, analyzes it, and sends back small numbers like how far off each note was or which sounds you mispronounced. Your AI then explains those numbers to you in plain words and suggests one thing to focus on next time. It also keeps a progress log so you can see how you are improving.

What you can do with it

Check how in tune you sing, note by note
Compare your singing to a MIDI melody or a musical key
Score your English pronunciation sound by sound
Measure your speaking pace, long pauses and filler words
Spot whether your voice sounds monotone or flat
Read your progress log to see how you are doing over time
Run guided practice sessions for singing, pronunciation or speaking

What it gives back to you

You get back short, clear answers in the chat. For singing you get things like how many notes were in tune and whether you tend to sing flat or sharp. For pronunciation you get a score per word and which sounds you confused, like saying s instead of th. For speaking you get your words per minute, your long pauses and the filler words you used, plus a transcript.

Before you start

What you need

The uv tool installed on your computer
espeak-ng installed (and optionally ffmpeg for m4a or aac files)
A microphone your computer is allowed to use
On macOS, an Apple Silicon Mac with macOS 14 or later for pronunciation analysis

Good to know

It uses your microphone while recording, saves audio and a progress log on your computer, and can send audio to Azure Speech only if you opt in.

Install it with your AI

Add Voice Coach MCP server to your AI, no technical skills needed

You don't install anything by hand. You copy one prompt, paste it into an AI that can work on your computer, and it checks, installs and connects the server for you, asking you when it needs something.

Sign in to get the install prompt

Members get a ready-made prompt that lets the Claude desktop app check Voice Coach MCP server, install it and connect it for them, step by step. You don't need any technical skills: you copy, paste and answer a few questions. Your connected AI can also find and install any of the 4,609 MCP servers here for you.