AI-Powered Meeting Analysis for Community Engagement
Transform long community meetings into actionable insights. Community Highlighter uses AI to analyze YouTube videos of town halls, city council meetings, school board sessions, and more.
- AI-Powered Summaries - Get concise summaries of hours-long meetings
- Entity Extraction - Automatically identify people, places, organizations, and projects
- Decision Timeline - Track when key decisions were made
- Cross-Meeting Analysis - Compare multiple meetings and build knowledge graphs
- Clip Creation - Select and export video clips (desktop app only)
- AI Meeting Assistant - Ask questions about the meeting content
- Transcript Search - Full-text search with timestamp navigation
- Multi-language Support - Translate transcripts to 8+ languages
Option A: App Bundle (Recommended)
- Download and extract the ZIP file
- Drag
Community Highlighter.appto your Applications folder - Double-click to launch
- Enter your OpenAI API key when prompted
- Click "Start Server" - the app opens in your browser!
First Launch Security Note: If you see "Community Highlighter can't be opened because it is from an unidentified developer":
- Right-click (or Control-click) on the app
- Select "Open" from the menu
- Click "Open" in the dialog that appears
- This is only needed once - future launches work normally
Option B: Command Line
cd community-highlighter-v6.0
python3 launcher.py- Download and extract the ZIP file
- Double-click
Community-Highlighter.bat - Enter your OpenAI API key when prompted
- The app opens in your browser!
Security Note: If Windows SmartScreen appears, click "More info" then "Run anyway"
An OpenAI API key is required to use the AI features. Here's how to get one:
-
Go to OpenAI's website
- Visit: platform.openai.com/api-keys
-
Create an account (or sign in)
- Click "Sign up" if you don't have an account
- You can sign up with Google, Microsoft, or email
-
Add payment method (required for API access)
- Go to Settings → Billing
- Add a payment method
- Note: You only pay for what you use (~$0.10-0.30 per meeting)
-
Create an API key
- Go to API Keys section
- Click "Create new secret key"
- Give it a name like "Community Highlighter"
- Copy the key immediately (it starts with
sk-) - You won't be able to see it again!
-
Paste in the app
- Launch Community Highlighter
- Paste your API key in the field
- Click "Save API Key"
OpenAI charges based on usage:
- Typical 2-hour meeting: $0.10 - $0.30
- You control the spending: Set limits in your OpenAI dashboard
- Free tier: New accounts get $5 free credits
A YouTube API key improves transcript fetching reliability but is not required.
- Go to console.cloud.google.com
- Create a new project
- Enable the YouTube Data API v3
- Create credentials (API Key)
- Add it to the app settings
- Python: 3.9 or higher
- OS: Windows 10+, macOS 10.14+, or Linux
- RAM: 4GB minimum, 8GB recommended
- Internet: Required for AI features and YouTube access
- Install Python from python.org/downloads
- On Windows, check "Add Python to PATH" during installation
- On Mac, you may need to install from python.org even if you have the system Python
If the app won't open:
- Right-click the app (not double-click)
- Select "Open" from the context menu
- Click "Open" in the security dialog
- This only needs to be done once
Or in Terminal:
xattr -cr "/Applications/Community Highlighter.app"- Make sure your key starts with
sk- - Check that you've added billing to your OpenAI account
- Verify the key is saved (check the app's status message)
- The video must have captions (auto-generated or manual)
- Try a different video to test
- Some videos block third-party access to captions
- Make sure you have Python 3.9 or higher:
python3 --version - Check that all dependencies installed correctly
- Try running from Terminal to see error messages:
cd "/Applications/Community Highlighter.app/Contents/Resources" python3 launcher.py
community-highlighter-v6.0/
├── Community Highlighter.app # macOS application (Mac only)
├── Community-Highlighter.bat # Windows launcher
├── launcher.py # GUI launcher
├── desktop_app.py # Server launcher
├── requirements.txt # Python dependencies
├── README.md # This file
├── backend/
│ ├── app.py # FastAPI server
│ └── .env.example # API key template
└── dist/ # Frontend build
# Clone the repository
git clone https://github.com/amateurmenace/community-highlighter.git
cd community-highlighter
# Install frontend dependencies
npm install
# Build frontend
npm run build
# Install backend dependencies
pip install -r requirements.txt
# Build Mac app
python build_mac_app.py
# Or run directly
python launcher.pyMIT License - See LICENSE for details.
Designed and developed by Stephen Walter at Brookline Interactive Group
In partnership with NeighborhoodAI.org
Built with React, FastAPI, OpenAI GPT, and Community
- Issues: GitHub Issues
- Email: stephen@weirdmachine.org
- Website: weirdmachine.org