A modern web app that transcribes meeting audio and generates intelligent, actionable summaries using state-of-the-art AI.
- Audio Transcription: Upload your meeting audio and get fast, accurate transcripts powered by Deepgram.
- AI Summarization: Receive concise summaries, key points, and action items using OpenRouter LLMs.
- Beautiful UI: Clean, responsive interface with drag-and-drop upload, progress indicators, and clear results.
- Easy Deployment: Ready for Vercel, Railway, Render, or any Python host.
-
Clone the repository:
git clone https://github.com/yocho1/AI-Powered-Meeting-Assistant.git cd AI-Powered-Meeting-Assistant/meeting-assistant -
Set up environment variables:
- Copy
.env.exampleto.env:cp .env.example .env
- Get your free Deepgram API key and OpenRouter API key.
- Edit
.envand fill in:DEEPGRAM_API_KEY=your_deepgram_api_key_here OPENROUTER_API_KEY=your_openrouter_api_key_here
- Copy
-
Install dependencies:
pip install -r requirements.txt
-
Run the app:
python app.py
Open http://localhost:5000 in your browser.
- Upload your meeting audio (mp3, wav, m4a, aac, ogg, webm, flac).
- Click Process Meeting.
- View the Meeting Transcript and AI Summary (with key points and action items).
meeting-assistant/
├── app.py # Flask backend
├── requirements.txt # Python dependencies
├── .env.example # Environment variable template
├── static/
│ ├── css/style.css # UI styles
│ └── js/main.js # Frontend logic
└── templates/
└── index.html # Main web page
- Transcription: Deepgram Speech-to-Text
- Summarization: OpenRouter LLMs
- Deploy on Railway, Render, Vercel, or any Python host.
- Set your environment variables (
DEEPGRAM_API_KEY,OPENROUTER_API_KEY) in your deployment dashboard.
MIT License. See LICENSE for details.
If you run into issues, open an issue on GitHub or ask for help!