A modern, browser-based transcription and translation application built with React. Free-Scribe leverages cutting-edge machine learning models running entirely in your browser via Web Workers, ensuring privacy and eliminating the need for server-side processing.

• 🎯 Audio Transcription: Convert speech to text using OpenAI's Whisper models
• 🌍 Multi-language Translation: Translate transcribed text into 22+ supported languages
• 🔒 Privacy-First: All processing happens locally in your browser - no data leaves your device
• ⚡ Real-time Processing: Powered by Web Workers for non-blocking UI performance
• 📱 Responsive Design: Works seamlessly across desktop and mobile devices
• 🚀 No Installation Required: Run directly in your web browser

Experience Free-Scribe in action: https://free-scribe-alpha.vercel.app/

• Frontend: React 18 with modern hooks and functional components
• Build Tool: Vite for fast development and optimized production builds
• Styling: Tailwind CSS for responsive and modern UI design
• ML Models:
  • OpenAI Whisper for speech-to-text transcription
  • Helsinki-NLP OPUS-MT models for translation
• Runtime: Web Workers for background ML model processing
• Package Manager: npm

Free-Scribe supports translation to the following languages:

European Languages: French, Spanish, German, Italian, Portuguese, Russian, Dutch, Polish, Czech, Finnish, Swedish, Danish, Norwegian Bokmål, Hungarian, Romanian, Ukrainian, Turkish

Asian Languages: Chinese (Simplified), Japanese, Korean, Hindi

Middle Eastern Languages: Arabic

• Node.js (version 16 or higher)
• npm or yarn package manager
• Modern web browser with Web Workers support

1. Clone the repository

   git clone https://github.com/MaheshR03/free-scribe.git
   cd free-scribe

2. Install dependencies

   npm install

3. Start the development server

   npm run dev

4. Open your browser Navigate to http://localhost:5173 to start using Free-Scribe

npm run build

The built application will be available in the dist directory.

1. Upload Audio: Click to upload an audio file or record directly in the browser
2. Transcribe: The app will automatically transcribe your audio using Whisper models
3. Translate: Select your target language and click translate to convert the text
4. Export: Copy or download your transcribed and translated content

free-scribe/
├── src/
│   ├── components/          # React components
│   │   ├── FileDisplay.jsx  # Audio file handling
│   │   ├── Header.jsx       # Application header
│   │   ├── HomePage.jsx     # Landing page
│   │   ├── Information.jsx  # Main app container
│   │   ├── Transcribing.jsx # Transcription UI
│   │   ├── Transcription.jsx# Transcription results
│   │   └── Translation.jsx  # Translation interface
│   ├── utils/              # Utility functions and workers
│   │   ├── presets.js      # Language definitions and constants
│   │   ├── translate.worker.js # Translation Web Worker
│   │   └── whisper.worker.js   # Transcription Web Worker
│   ├── App.jsx             # Main app component
│   └── main.jsx            # Application entry point
├── public/                 # Static assets
├── package.json           # Project dependencies
└── README.md              # This file

We welcome contributions to Free-Scribe! Please feel free to submit issues, feature requests, or pull requests.

1. Fork the repository
2. Create your feature branch (git checkout -b feature/AmazingFeature)
3. Commit your changes (git commit -m 'Add some AmazingFeature')
4. Push to the branch (git push origin feature/AmazingFeature)
5. Open a Pull Request

This project is licensed under the MIT License - see the LICENSE file for details.

• OpenAI Whisper for speech-to-text capabilities
• Hugging Face Transformers for browser-based ML model inference
• Helsinki-NLP for high-quality translation models
• Xenova Transformers.js for running transformers in the browser

If you encounter any issues or have questions, please file an issue on the GitHub repository.

Made with ❤️ for the open-source community