An intelligent language learning application that helps users practice speaking in different languages through AI-powered conversations. The app provides real-time speech recognition, translation, and personalized feedback to improve language fluency.

• Real-time speech recognition in multiple languages (Spanish, French, Hindi, English)
• Voice-to-text conversion with Google Speech Recognition API
• Interactive conversations with AI native speakers
• Text-to-speech responses in the target language

• OpenAI GPT-3.5 Turbo integration for natural conversations
• Contextual responses that guide conversations on specific topics
• Automatic translation to English for better understanding
• Personalized feedback with fluency scoring (1-10 scale)

• Session statistics including time spent and number of practice sessions
• Performance analytics with average fluency scores
• Detailed feedback history with specific improvement suggestions
• Firebase integration for persistent data storage

• Firebase Authentication with email/password and Google sign-in
• Secure session management
• User dashboard with personalized experience

• Python 3.8 or higher
• Microphone for speech input
• Speakers for audio output
• OpenAI API key
• Firebase project with authentication and Firestore enabled

1. Clone the repository

   git clone <repository-url>
   cd LingoLearn-AI

2. Create and activate virtual environment

   python -m venv venv
   source venv/bin/activate  # On Windows: venv\Scripts\activate

3. Install dependencies

   pip install -r requirements.txt

4. Set up environment variables Create a .env file in the root directory:

   OPENAI_API_KEY=your_openai_api_key_here

5. Configure Firebase

   • Download your Firebase service account key as key.json
   • Place it in the root directory
   • Enable Authentication and Firestore in your Firebase console

python app.py

Navigate to http://localhost:5000 in your browser.

streamlit run app2.py

The Streamlit interface will open automatically in your browser.

1. Login with your email or Google account
2. Select your target language (Spanish, French, Hindi)
3. Click "Speak" to start voice recognition
4. Have a conversation with the AI native speaker
5. End the session to receive personalized feedback
6. View your progress in the dashboard

1. Launch the app and select "Chat" from the sidebar
2. Set your language by clicking "Detect Language" or manually selecting
3. Click "Speak" to begin voice recognition
4. Practice conversation with the AI assistant
5. End conversation to get detailed feedback
6. Check statistics in the Statistics page

• Backend: Python, Flask, Streamlit
• AI/ML: OpenAI GPT-3.5 Turbo, LangChain
• Speech Processing: SpeechRecognition, Google Speech API
• Database: Firebase Firestore
• Authentication: Firebase Auth
• Frontend: HTML, CSS, JavaScript, Bootstrap

LingoLearn AI/
├── app.py                 # Flask web application
├── app2.py               # Streamlit interface
├── requirements.txt      # Python dependencies
├── key.json             # Firebase service account key
├── .env                 # Environment variables
├── static/              # Static assets
│   ├── css/
│   └── js/
├── templates/           # HTML templates
│   ├── base.html
│   ├── index.html
│   └── dashboard.html
└── venv/               # Virtual environment

1. Sign up at OpenAI
2. Generate an API key
3. Add it to your .env file

1. Create a Firebase project at Firebase Console
2. Enable Authentication and Firestore
3. Download service account key as key.json
4. Configure authentication methods (Email/Password, Google)

The app uses Google's Speech Recognition API which requires an internet connection. Supported languages:

• Spanish (es)
• French (fr)
• Hindi (hi)
• English (en)

• Contextual responses: AI maintains conversation context
• Topic guidance: AI introduces specific topics and questions
• Brief responses: Keeps conversations natural and engaging
• Language-specific voices: Different TTS voices for each language

• Fluency scoring: 1-10 rating based on conversation quality
• Specific improvements: 3 targeted suggestions with conversation citations
• Progress tracking: Historical data and performance trends
• Session analytics: Time spent, session count, average scores

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.

• OpenAI for providing the GPT-3.5 Turbo API
• Google for Speech Recognition and Text-to-Speech services
• Firebase for authentication and database services
• LangChain for AI/ML framework
• Streamlit for the interactive web interface

If you encounter any issues or have questions:

1. Check the Issues page
2. Create a new issue with detailed description
3. Include error messages and system information

Happy Learning! 🌍🗣️