SpeakSum 📱📄🔊

An Android application that extracts text from PDF files, generates intelligent summaries, and reads them aloud using Text-to-Speech technology.

✨ Features

• PDF Text Extraction: Extracts text content from PDF documents using PDFBox
• Text-to-Speech (TTS): Reads summaries aloud with play/pause controls
• Modern UI: Built with Jetpack Compose and Material Design 3
• Real-time Processing: Displays loading indicators during PDF processing
• Error Handling: User-friendly error messages for various failure scenarios

🛠️ Technology Stack

• Language: Kotlin
• UI Framework: Jetpack Compose
• Architecture: MVVM (Model-View-ViewModel)
• Concurrency: Kotlin Coroutines
• PDF Processing: PDFBox for Android
• Text-to-Speech: Android TTS API
• Material Design: Material 3 Components

🏛️ Architecture Overview

📦 Components

1. MainActivity: Entry point that sets up the Compose UI theme
2. MainScreen: Main composable containing the UI layout and interactions
3. SViewModel: ViewModel managing app state and business logic

🔑 Key Features Implementation

📄 PDF Processing

• Uses PDFBox library to load and extract text from PDF files
• Runs on IO dispatcher to prevent blocking the main thread
• Handles file URI selection through Android's document picker

📝 Summary Generation

The app uses a keyword-based extraction algorithm:

• Splits text into sentences
• Prioritizes sentences containing keywords: "important", "conclusion", "result", "found", "shows", "indicates", "summary", "key"
• Falls back to longest sentences if no keyword matches
• Limits summary to 3-5 sentences and 1000 characters

🔊 Text-to-Speech

• Initializes TTS engine with US English locale
• Tracks speaking state with real-time updates
• Provides play and stop controls
• Handles TTS lifecycle properly

📊 App States

The ViewModel manages several states:

• isProcessing: Shows loading indicator during PDF processing
• errorMessage: Displays error messages to users
• summary: Stores the generated summary text
• isSpeaking: Indicates if TTS is currently active
• ttsReady: Confirms TTS engine initialization status

🔧 Setup Steps

1. 📥 Clone the repository

   git clone https://github.com/yourusername/SpeakSum.git
   cd SpeakSum

🎯 How It Works

Workflow

📄 PDF Selection → 📖 Text Extraction → 🧠 Summary Generation → 📋 Display → 🔊 TTS Playback

🤝 Contributing

We welcome contributions from the community! 🎉

⭐ Show Your Support

If you find this project helpful, please consider:

• Starring the repository
• Forking and contributing
• Sharing with others
• Reporting bugs
• Suggesting new features