A smart meeting assistant that uses Gemini LLM to analyze meeting notes and Stream Video for real-time video conferencing.
.
├── backend/ # Express backend
│ ├── src/
│ │ └── index.js # Main server file
│ ├── package.json
│ └── .env.example # Environment variables template
│
└── frontend/ # React + Vite frontend
├── src/
│ ├── components/
│ │ ├── Header.jsx
│ │ ├── MeetingAnalyzer.jsx
│ │ └── VideoCall.jsx
│ ├── App.jsx
│ └── main.jsx
├── package.json
└── vite.config.js
- Node.js (v14 or higher)
- npm or yarn
- Gemini API key from Google AI Studio
- Stream API key and secret from Stream Dashboard
-
Navigate to the backend directory:
cd backend
-
Install dependencies:
npm install
-
Create a .env file:
cp .env.example .env
-
Add your API keys to the .env file:
PORT=5000 GEMINI_API_KEY=your_gemini_api_key_here STREAM_API_KEY=your_stream_api_key_here STREAM_API_SECRET=your_stream_api_secret_here
-
Navigate to the frontend directory:
cd frontend
-
Install dependencies:
npm install
-
Create a .env file:
cp .env.example .env
-
Add your Stream API key to the .env file:
VITE_STREAM_API_KEY=your_stream_api_key_here
- In the backend directory:
The server will start on http://localhost:5000
npm run dev
- In the frontend directory:
The application will be available at http://localhost:3000
npm run dev
- Real-time video conferencing with Stream Video
- Create or join meetings
- Video and audio controls
- Screen sharing capabilities
- Paste meeting notes into the text area
- Get AI-powered analysis of:
- Key discussion points
- Action items
- Decisions made
- Follow-up tasks
- Modern, responsive UI using Material-UI
- Real-time analysis using Gemini LLM
-
Frontend:
- React
- Vite
- Material-UI
- Stream Video React SDK
- Axios
-
Backend:
- Express.js
- Google Generative AI (Gemini)
- Stream Video Server SDK
- CORS
- dotenv