📖 AI Reading Practice Buddy 🎙️

An AI-powered reading practice application that helps students improve their reading fluency and pronunciation through speech recognition and feedback.

Features

• Story Generation: AI-generated age-appropriate stories based on custom topics
• Speech-to-Text Assessment: Record your reading and get detailed feedback
• Text-to-Speech: Listen to proper pronunciation (when available)
• Reading Analysis: Compare your reading with the original text and get specific improvement suggestions

How It Works: An Agentic System

This application demonstrates an "agentic" approach by coordinating multiple specialized AI components:

1. The Storyteller Agent (LLM): Uses Google's Gemini model to create unique, grade-appropriate reading passages
2. The Orator Agent (Text-to-Speech): Converts text to natural-sounding speech using Facebook's MMS-TTS
3. The Scribe Agent (Speech-to-Text): Uses OpenAI's Whisper model to transcribe spoken words
4. The Analyst Agent: Compares original text with your reading to provide detailed feedback
5. The Conductor: The Gradio interface orchestrates all components

Setup

1. Clone the repository:

   git clone https://github.com/yourusername/reading-practice-buddy.git
   cd reading-practice-buddy

2. Create a virtual environment:

   python -m venv read_along
   source read_along/bin/activate  # On macOS/Linux

3. Install dependencies:

   pip install -r requirements.txt

4. Set up environment variables: Create a .env file and add your Google API key:

   GOOGLE_API_KEY=your_google_api_key_here
   

5. Run the application:

   python app1.py

6. Open your browser and go to the URL shown in the terminal (typically http://127.0.0.1:7860)

Usage

1. Story Setup: Enter a name (optional), select grade level, and provide a story topic
2. Generate Story: Click "Generate Story Text" to create a custom reading passage
3. Listen (Optional): Generate audio to hear proper pronunciation
4. Record: Use the microphone to record yourself reading the passage
5. Assessment: Get detailed feedback on your reading accuracy

Requirements

• Python 3.8+
• Google Generative AI API key
• Internet connection for AI services

Technologies Used

• Gradio: Web interface framework
• Google Gemini: Story generation
• OpenAI Whisper: Speech-to-text transcription
• Facebook MMS-TTS: Text-to-speech synthesis
• Python difflib: Text comparison and analysis

Contributing

This project was created as a demonstration for an AI hackathon. Feel free to fork and improve!

License

MIT License - feel free to use and modify as needed.