AI-powered web app that allows users to transcribe audio, extract text from images, summarize content, generate MCQs, and more. Built using the MERN stack with Vite for the frontend.
- 🎙️ Voice-to-Text using MP3 URLs
- 🖼️ Image-to-Text via OCR
- ✂️ Text Summarization (TensorFlow.js powered)
- 🧪 MCQ Generator
- 📝 Manual Note Editor
- 🔐 Google Login Authentication (Required)
git clone https://github.com/your-username/notegenius.git
cd notegenius
# Install backend dependencies
cd backend
npm install
# Install frontend dependencies
cd ../frontend
npm install
npm install @tensorflow/tfjs @tensorflow-models/universal-sentence-encoder
npm install axios
# Then use AssemblyAI's API in backend routes
npm install openai
npm install @xenova/transformers
# Note: This runs models in-browser (with WebAssembly), no server needed
Create a .env
file in the /backend
directory:
MONGO_URI=your_mongodb_connection_string
PORT=5000
OPENAI_API_KEY=your_openai_key
ASSEMBLYAI_API_KEY=your_assemblyai_key
🔐 Never expose this file publicly! Add
.env
to.gitignore
.
In two terminal windows or tabs:
# Terminal 1: Start backend
cd backend
npm start
# Terminal 2: Start frontend
cd frontend
npm run dev
Install Google login packages:
npm install @react-oauth/google jwt-decode
Create a .env
in the /frontend
folder if needed:
VITE_GOOGLE_CLIENT_ID=your_google_oauth_client_id
Open your browser at:
http://localhost:5173
(Frontend)
http://localhost:5000
(Backend)
notegenius/
│
├── backend/
│ ├── server.js
│ ├── routes/
│ └── ...
│
├── frontend/
│ ├── App.jsx
│ ├── components/
│ └── main.jsx
│
└── README.md