Skip to main content

Offline meeting transcription for macOS with automatic meeting detection

Project description

Meeting Noter

Offline meeting transcription tool for macOS. Captures both your voice and meeting participants' audio, saves to MP3, and transcribes locally using Whisper.

Features

  • No setup required - Just install and run
  • Captures both sides - Your mic + system audio (meeting participants)
  • Offline transcription - Uses Whisper locally, no API calls
  • Auto-detection - Detects active meetings (Zoom, Teams, Meet, Slack)
  • Multiple interfaces - Menu bar app, desktop GUI, or CLI
  • Auto-segmentation - One file per meeting (detects silence)

Installation

# Install dependencies
brew install ffmpeg lame pkg-config python@3.12

# Install meeting-noter (use Python 3.12 for best compatibility)
pipx install meeting-noter --python /opt/homebrew/bin/python3.12

Or with pip:

pip install meeting-noter

Quick Start

Menu Bar App (recommended):

meeting-noter menubar

Desktop GUI:

meeting-noter gui

CLI Recording:

meeting-noter start "Weekly Standup"

The app will request microphone and Screen Recording permissions on first use.

Usage

Recording

  • The menu bar app auto-detects meetings and prompts to record
  • Or manually start recording via the GUI/CLI
  • Press Ctrl+C (CLI) or click Stop to end recording

Transcription

Recordings are auto-transcribed by default. Or manually:

# Transcribe the most recent recording
meeting-noter transcribe

# Transcribe a specific file
meeting-noter transcribe recording.mp3

# List all recordings
meeting-noter list

Commands

Command Description
meeting-noter Launch desktop GUI
meeting-noter menubar Launch menu bar app
meeting-noter gui Launch desktop GUI
meeting-noter start [name] Interactive CLI recording
meeting-noter list List recent recordings
meeting-noter transcribe Transcribe a recording
meeting-noter devices List audio devices
meeting-noter status Check daemon status

Options

start

  • First argument: Meeting name (optional, auto-generates timestamp if omitted)

transcribe

  • -m, --model: Whisper model size (tiny.en, base.en, small.en, medium.en, large-v3)
  • -o, --output-dir: Directory with recordings

list

  • -n, --limit: Number of recordings to show
  • -o, --output-dir: Directory with recordings

How It Works

┌─────────────────────────────────────┐
│         Your Meeting App            │
│      (Zoom/Teams/Meet/Slack)        │
└──────────────────┬──────────────────┘
                   │
     ┌─────────────┴─────────────┐
     ▼                           ▼
┌─────────┐               ┌─────────────┐
│   Mic   │               │ System Audio│
│(default)│               │(ScreenCaptureKit)
└────┬────┘               └──────┬──────┘
     │                           │
     └───────────┬───────────────┘
                 ▼
         ┌─────────────┐
         │Meeting Noter│
         │  (capture)  │
         └──────┬──────┘
                │
                ▼
    ~/meetings/2024-01-15_Weekly_Standup.mp3
                │
                ▼ (auto or on-demand)
         ┌─────────────┐
         │   Whisper   │ (local)
         └──────┬──────┘
                │
                ▼
    ~/meetings/2024-01-15_Weekly_Standup.txt

Permissions

On first use, macOS will ask for:

  1. Microphone - For capturing your voice
  2. Screen Recording - For capturing system audio (meeting participants)

Grant these in System Settings > Privacy & Security.

Configuration

Config file: ~/.config/meeting-noter/config.json

{
    "recordings_dir": "~/meetings",
    "transcripts_dir": "~/meetings",
    "whisper_model": "tiny.en",
    "auto_transcribe": true,
    "silence_timeout": 5,
    "capture_system_audio": true
}

Whisper Models

Model Size Speed Accuracy
tiny.en ~75MB Fastest Good
base.en ~150MB Fast Better
small.en ~500MB Medium High
medium.en ~1.5GB Slow Very High
large-v3 ~3GB Slowest Best

Requirements

  • macOS 12.3+ (for ScreenCaptureKit)
  • Python 3.9+ (3.12 recommended for best compatibility)
  • FFmpeg (brew install ffmpeg) - required for audio processing
  • LAME (brew install lame) - required for MP3 encoding
  • pkg-config (brew install pkg-config) - required for building dependencies

License

MIT

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

meeting_noter-0.5.1.tar.gz (70.5 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

meeting_noter-0.5.1-py3-none-any.whl (79.1 kB view details)

Uploaded Python 3

File details

Details for the file meeting_noter-0.5.1.tar.gz.

File metadata

  • Download URL: meeting_noter-0.5.1.tar.gz
  • Upload date:
  • Size: 70.5 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.9.6

File hashes

Hashes for meeting_noter-0.5.1.tar.gz
Algorithm Hash digest
SHA256 20710926bb7c16f6ef759c5d22ecdeea10179daf6d864cbb645457103698f55a
MD5 6f7b6bbb548e724b9ea3a92b64a921c8
BLAKE2b-256 47ee2f8da5fe11b10ae14d19c9e207f4d9069b7db01968a0afd754f565253d04

See more details on using hashes here.

File details

Details for the file meeting_noter-0.5.1-py3-none-any.whl.

File metadata

  • Download URL: meeting_noter-0.5.1-py3-none-any.whl
  • Upload date:
  • Size: 79.1 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.9.6

File hashes

Hashes for meeting_noter-0.5.1-py3-none-any.whl
Algorithm Hash digest
SHA256 7fe06833041e613e7562d647692095c18bd1dc4da422a79a72622dd02a06bb5f
MD5 be660cafb470828bed2a2787f6b1de42
BLAKE2b-256 cc59183777abb48e0dad60684f5b4b598fb8f811cf1ccf180323410f04f2c37d

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page