Transcripted MCP server

Transcripted

Private meeting notes that never leave your Mac. No bot joins your call.

Transcripted is a free, open-source Mac app for meeting notes and dictation. It transcribes on your Mac and saves plain Markdown files you own. You can search them, or let your AI read them.

Install with Homebrew · Interactive demo · transcripted.app

<!-- Demo: an 18-second tour built from app screenshots. To replace it with a real screen recording, follow docs/marketing/hero-video-storyboard.md. -->

What it does

records your mic and your Mac's audio, so it hears both sides and nothing joins the call.

• Records any meeting. Zoom, Meet, Teams, FaceTime, or in person. It

before meetings on your calendar.

• Notices when a call starts. It offers to record. It can also remind you

and it suggests their name the next time they talk. For in-person meetings, turn on People in the room in Settings.

• Knows who's talking. It splits the call by speaker. Name someone once,

were typing.

• Types what you say. Tap a key, talk, and your words show up where you

what you write, in every app or just the ones you pick, so your AI has it too. It can also suggest the next few words as you type.

• Transcribes files. Drop in an audio or video file you already have.
• Helps you write, if you want (coming in 1.1.67). Turn on Writing to save

<!-- When 1.1.67 ships, drop "(coming in 1.1.67)" here and in Requirements. -->

Everything runs on your Mac. The speech models ship inside the app, so transcription works offline.

Your notes are plain files

Each meeting becomes a Markdown file with timestamps and speaker names. Here's one, trimmed:

---
title: "Product Review Sync"
capture_type: meeting
date: 2026-05-13
duration: "18:42"
transcription_engine: parakeet_local
sources: [mic, system_audio]
---

# Product Review Sync

Recorded May 13, 2026 at 3:05 PM  •  18 min, 42 sec  •  1864 words  •  27 turns

## Transcript

**00:00**  [Mic/You]
Let's capture launch feedback and decide what needs follow-up.

Shortened. The full README is on GitHub.