Smart Notes Transcriber

This project is a web application that transcribes audio notes and generates quizzes from them. It uses OpenAI's Whisper for transcription and a GPT model for formatting notes and creating quizzes. The frontend is built with Streamlit, and the backend is a FastAPI application.

Features

• Audio Transcription: Record audio directly in the browser or upload an audio file to get it transcribed.
• AI-Powered Note Formatting: Use different note styles (e.g., detailed, summary, bullet points) and custom templates to format the transcribed text.
• Automatic Quiz Generation: Automatically generate a multiple-choice quiz based on the content of your notes.
• Note Management: View, search, and filter your notes.
• Tagging System: Organize your notes with tags.
• Download and Share: Download your notes as Markdown files.

Project Structure

.
├── backend/
│   ├── app/
│   │   ├── __init__.py
│   │   ├── main.py         # FastAPI application
│   │   ├── database.py     # Database logic
│   │   └── quiz.py         # Quiz generation logic
│   └── requirements.txt    # Backend dependencies
├── frontend/
│   ├── app.py              # Streamlit application
│   └── requirements.txt    # Frontend dependencies
└── README.md

Getting Started

Prerequisites

• Python 3.7+
• pip

Installation

1. Clone the repository:

   git clone <repository-url>
   cd <repository-name>

2. Set up the backend:

   cd backend
   python -m venv venv
   source venv/bin/activate  # On Windows, use `venv\Scripts\activate`
   pip install -r requirements.txt

3. Set up the frontend:

   cd ../frontend
   python -m venv venv
   source venv/bin/activate  # On Windows, use `venv\Scripts\activate`
   pip install -r requirements.txt

Configuration

The backend requires an OpenAI API key.

1. Create a .env file in the backend directory.
2. Add your OpenAI API key to the .env file:

   OPENAI_API_KEY="your-openai-api-key"
   

Running the Application

1. Start the backend server:

   • Navigate to the backend directory.
   • Make sure your virtual environment is activated.
   • Run the following command:

     uvicorn app.main:app --reload

   • The backend will be running at http://localhost:8000.

2. Start the frontend application:

   • Navigate to the frontend directory.
   • Make sure your virtual environment is activated.
   • Run the following command:

     streamlit run app.py

   • The frontend will be accessible in your browser, usually at http://localhost:8501.

API Endpoints

The backend provides the following main API endpoints:

• POST /transcribe/: Transcribes audio, formats notes, and generates a quiz.
• GET /notes/: Retrieves all notes.
• GET /notes/{note_id}: Retrieves a specific note by its ID.
• GET /notes/search/: Searches for notes by content and tags.
• GET /tags/: Retrieves all unique tags.
• POST /templates/upload/: Uploads a custom note formatting template.
• GET /templates/: Retrieves a list of available templates.