Transearly is an innovative AI-powered translation platform that combines advanced computer vision with natural language processing to provide seamless, real-time translation services. The platform supports multiple translation modes including text, voice, image, and document translation.

• 📸 Image Translation with OCR - Detect and translate text in images using Google Cloud Vision API
• 🎤 Voice Translation - Real-time speech-to-text translation
• 📄 Document Translation - Support for PDF, DOCX, XLSX, PPTX, CSV formats
• 💬 Text Translation - Fast and accurate text translation across 8+ languages
• 📱 Mobile-First Design - Beautiful React Native mobile application
• ⚡ Real-time Processing - WebSocket integration for live translation updates
• 🎨 Interactive UI - Bounding box detection with tap-to-translate popups

• Smart OCR Detection - Uses Google Cloud Vision API for accurate text detection
• Interactive Bounding Boxes - Tap on detected text regions to view translations
• Multi-language Support - Automatically detects and translates text in images
• Paragraph Grouping - Intelligently groups text into meaningful segments

• Real-time Recording - Record and translate voice input
• Speech-to-Text - Google Cloud Speech API for accurate transcription
• Audio File Support - MP3, WAV, FLAC, OGG, WEBM formats
• Auto Translation - Automatically translates transcribed text
• Multiple Languages - Support for 8+ languages

• File Format Support - PDF, DOCX, XLSX, PPTX, CSV
• Batch Processing - Queue-based translation for large documents
• Progress Tracking - Real-time translation progress via WebSocket
• Format Preservation - Maintains original document formatting

• Instant Translation - Fast text-to-text translation
• Context-Aware - Preserves semantic meaning
• Copy to Clipboard - Easy result sharing

┌─────────────────────────────────────────────────────────────┐
│                    TRANSEARLY PLATFORM                       │
└─────────────────────────────────────────────────────────────┘

┌──────────────────────┐         ┌──────────────────────────┐
│   Mobile App         │         │   Backend API            │
│   (React Native)     │◄───────►│   (NestJS)               │
│                      │   REST  │                          │
│  • Camera Screen     │   WebSocket  • Translation Service │
│  • Voice Recording   │         │   • Queue Processing     │
│  • Text Input        │         │   • Google Vision OCR    │
│  • File Upload       │         │   • AI Translation       │
└──────────────────────┘         └──────────────────────────┘
                                           │
                    ┌──────────────────────┼──────────────────┐
                    │                      │                  │
              ┌─────▼──────┐      ┌───────▼──────┐   ┌──────▼─────┐
              │  Google    │      │  OpenRouter  │   │   Redis    │
              │  Cloud     │      │  (Gemini)    │   │   Queue    │
              │  Vision    │      │              │   │            │
              └────────────┘      └──────────────┘   └────────────┘

transearly/
├── transearly-api/          # Backend NestJS API Server
│   ├── src/
│   │   ├── modules/
│   │   │   └── translator/  # Translation services & controllers
│   │   ├── main.ts
│   │   └── app.module.ts
│   └── package.json
│
└── mobile-app/              # React Native Mobile Application
    ├── src/
    │   ├── screens/         # App screens
    │   ├── components/      # Reusable components
    │   ├── services/        # API integration
    │   └── navigation/      # Navigation setup
    └── package.json

• Node.js 18+
• npm or yarn
• Expo CLI (for mobile app)
• Google Cloud Vision API credentials
• OpenRouter API key

git clone https://github.com/your-org/transearly.git
cd transearly

cd transearly-api
npm install

# Create .env file
cp .env.example .env

# Add your credentials to .env
GOOGLE_APPLICATION_CREDENTIALS=./google-cloud-key.json
OPENROUTER_API_KEY=your_openrouter_key
OPENROUTER_BASE_URL=https://openrouter.ai/api/v1/chat/completions
OPENROUTER_MODEL=google/gemini-2.0-flash-exp:free

# Start the server
npm run start:dev

The API will run on http://localhost:5010

cd mobile-app
npm install

# Create .env file
cp .env.example .env

# Update API_URL in src/config/api.config.js
# For local development: http://YOUR_LOCAL_IP:5010

# Start the app
npm start
# or use tunnel mode
npm run tunnel

1. Go to Google Cloud Console
2. Create a new project or select existing one
3. Enable the following APIs:
   • Cloud Vision API (for image OCR)
   • Cloud Speech-to-Text API (for audio transcription)
4. Create a Service Account and download JSON key
5. Save the key as google-cloud-key.json in transearly-api/

• Framework: NestJS (Node.js)
• Queue: Bull + Redis
• OCR: Google Cloud Vision API
• Speech-to-Text: Google Cloud Speech API
• AI Translation: OpenRouter (Gemini Flash)
• WebSocket: Socket.io
• Document Processing: pdf-lib, mammoth, exceljs, pptxgenjs

• Framework: React Native + Expo
• UI Components: React Native core components
• Navigation: React Navigation
• HTTP Client: Axios
• Real-time: Socket.io Client
• Media: Expo Camera, Expo Audio

• Google Cloud Vision API - Text detection and OCR
• Google Cloud Speech API - Speech-to-Text transcription
• OpenRouter - AI translation (Gemini Flash model)
• Redis - Queue management

🇻🇳 Vietnamese | 🇬🇧 English | 🇪🇸 Spanish | 🇫🇷 French 🇩🇪 German | 🇯🇵 Japanese | 🇰🇷 Korean | 🇨🇳 Chinese

┌─────────────────────────────────┐
│  [<]  Image Translation    [🇻🇳] │
├─────────────────────────────────┤
│                                 │
│     ┌──────────────────┐        │
│     │  祝通宝玉萃院...  │◄─ Tap  │
│     └──────────────────┘        │
│                                 │
│  ┌─────────────────────────┐   │
│  │ Translation             │   │
│  │ Original: 祝通宝玉...    │   │
│  │ Translated: Chúc bạn... │   │
│  └─────────────────────────┘   │
│                                 │
│  [📷 Translate]                 │
└─────────────────────────────────┘

POST   /translator/text              # Translate text
POST   /translator/image             # Translate image with OCR
POST   /translator/audio             # Translate audio/voice (Speech-to-Text + Translation)
POST   /translator/upload            # Upload document for translation
GET    /translator/status/:jobId     # Check translation job status
GET    /translator/download/:fileName # Download translated document

{
  "success": true,
  "targetLanguage": "Vietnamese",
  "segments": [
    {
      "position": {
        "x": 15.5,
        "y": 20.3,
        "width": 30.2,
        "height": 5.1
      },
      "original": "祝 通 宝 玉 萃 院 之 旅 充 满 快 乐",
      "translated": "Chúc chuyến đi đến học viện Ngọc Bảo Tụy đầy niềm vui"
    }
  ]
}

{
  "success": true,
  "originalText": "Hello, how are you today?",
  "translatedText": "Xin chào, hôm nay bạn khỏe không?",
  "audioDetails": {
    "duration": 3,
    "language": "en-US"
  }
}

Trương Nguyễn Tiến Đạt Full-stack Developer

Nguyễn Minh Thắng Full-stack Developer

Nguyễn Bá Trung Nguyên Backend Developer

Nguyễn Hữu Anh Tuấn Backend Developer

✅ Text Translation ✅ Image Translation with OCR ✅ Voice Recording & Translation (Speech-to-Text + AI Translation) ✅ Audio File Support (MP3, WAV, FLAC, OGG, WEBM) ✅ Document Translation (PDF, DOCX, XLSX, PPTX, CSV) ✅ Real-time WebSocket Updates ✅ Interactive Bounding Box UI 🚧 Multi-language Audio Output 🚧 Offline Translation Mode 🚧 Translation History & Favorites

We welcome contributions! Please follow these steps:

1. Fork the repository
2. Create a 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.

• Google Cloud Vision API for powerful OCR capabilities
• OpenRouter for AI translation services
• NestJS for the robust backend framework
• Expo for streamlined React Native development

For questions or support, please open an issue or contact the team.