TTS Reader 🎧

A simple, privacy-focused text-to-speech web application powered by AI voices.

✨ Features

• 8 AI Voices - Multiple American and British accents
• Browser-Based - 100% local processing, no server required
• Privacy First - Your text never leaves your device
• Simple Interface - Clean, modern, and easy to use
• Audio Export - Download generated speech as WAV files

🚀 Quick Start

For Development

# Install dependencies
npm install

# Start development server
npm run dev

# Build for production
npm run build

GitHub Pages Deployment

This app is configured to automatically deploy to GitHub Pages:

1. Push changes to the main branch
2. GitHub Actions will automatically build and deploy
3. Your app will be live at: https://yourusername.github.io/TwelveReader-App/

No additional configuration needed!

🎯 Usage

1. Enter or paste text in the text area
2. Select a voice from the voice selector
3. Click "Generate Speech" to create audio
4. Use the audio controls to play, pause, and navigate
5. Download the audio if needed

🛠️ Tech Stack

• React - UI framework
• TypeScript - Type safety
• Kokoro AI - Neural voice synthesis
• Vite - Build tool
• Tailwind CSS - Styling

📦 Dependencies

• react - React library
• react-dom - React DOM rendering
• kokoro-js - Text-to-speech engine

🔒 Privacy

• All processing happens in your browser
• No data is sent to any server
• No tracking or analytics
• No account required

📄 License

MIT License - Free to use and modify

---

Made with ❤️ for simple, private text-to-speech