π Hackathon Project: AI for Social Good Category
An intelligent, inclusive English tutoring platform that leverages cutting-edge AI technology to democratize language learning and bridge communication barriers worldwide. Our mission is to make high-quality English education accessible to everyone, regardless of background, learning style, or physical abilities.
- Democratizing Education: Free, high-quality English tutoring for underserved communities
- Cultural Bridge: Helping immigrants, refugees, and international students integrate successfully
- Career Empowerment: Opening doors to better job opportunities through improved English skills
- Accessibility First: Voice-enabled learning for visual impairments and reading difficulties
- π International Students - Academic success support
- πΌ Job Seekers - Professional communication skills
- π Introverted Learners - Safe, judgment-free practice environment
- βΏ Accessibility Needs - Voice-first design for inclusive learning
- 8+ Specialized AI Tutors: Professional Interview Coach, Academic Writing Assistant, Casual Conversation Partner, Grammar Expert, Pronunciation Specialist, and more
- Custom Avatar Creation: Design your perfect tutor with personalized personality traits
- Adaptive Learning: AI adjusts to your pace, level, and learning style
- Real-time Corrections: Instant grammar, pronunciation, and fluency feedback
- Speech Recognition: Practice pronunciation with real-time feedback
- Text-to-Speech: Hear perfect pronunciation examples
- Hands-free Learning: Fully voice-controlled interface option
- Multi-modal Input: Type, speak, or combine both methods
- Pre-built Specialists: Choose from expertly crafted tutor personalities
- Custom Creation: Build your ideal tutor with specific traits and expertise
- Personality Profiles: Each avatar has unique teaching styles and specializations
- Emotional Intelligence: AI responds with appropriate emotional tone and support
- Context Awareness: AI remembers your learning journey and preferences
- Real-world Scenarios: Practice job interviews, academic presentations, daily conversations
- Progress Tracking: Monitor improvement across grammar, vocabulary, and fluency
- Session Memory: Continuous learning with persistent conversation history
Frontend: React 19.1.0 + Vite 6.2.0
AI Engine: Google Gemini AI (@google/genai 1.20.0)
Styling: TailwindCSS 4.1.11 with Glass Morphism Design
Routing: React Router 7.9.1
State: Context API (Voice, Avatar, Chat Contexts)
Storage: LocalStorage for persistence
APIs: Speech Recognition + Speech Synthesis
src/
βββ components/ # Reusable UI components
β βββ Avatar.jsx # Avatar display and management
β βββ ChatInput.jsx # Voice + text input system
β βββ ChatMessage.jsx # Intelligent message rendering
β βββ ChatWindow.jsx # Conversation interface
β βββ icons/ # Custom icon system
βββ contexts/ # State management
β βββ AvatarContext.jsx # Avatar and personality management
β βββ ChatContext.jsx # Conversation and session handling
β βββ VoiceContext.jsx # Speech recognition and synthesis
βββ pages/ # Route components
β βββ Landing.jsx # Social impact showcase
β βββ Chat.jsx # Main learning interface
β βββ Avatars.jsx # Avatar customization
β βββ Settings.jsx # User preferences
βββ services/ # Business logic
β βββ geminiService.js # Google AI integration
β βββ content.js # AI personality management
β βββ storageService.js # Data persistence
βββ utils/ # Helper functions
- Node.js 16 or higher
- Google Gemini API Key (Get it here)
- Modern web browser with microphone support
- Clone the repository
git clone <repository-url>
cd My-English-tutor- Install dependencies
npm install- Configure API Key
Create a
.envfile in the root directory:
VITE_GEMINI_API_KEY=your_gemini_api_key_here- Start the application
npm run dev- Open in browser
Navigate to
http://localhost:5173
- π― Choose Your Goal: Select your learning objective (career, academic, casual)
- π€ Pick Your Tutor: Choose from specialized AI avatars or create custom
- π€ Enable Voice: Allow microphone access for speech features
- π¬ Start Learning: Begin your personalized English learning journey
- Glass Morphism: Modern, accessible interface with sky-blue/violet theme
- Responsive Design: Seamless experience across desktop, tablet, and mobile
- Accessibility First: High contrast, keyboard navigation, screen reader support
- Intuitive Navigation: Clear user flow with minimal learning curve
- Welcome & Goal Setting: Personalized onboarding experience
- Avatar Selection: Choose or customize your perfect AI tutor
- Interactive Practice: Voice and text conversations with real-time feedback
- Progress Tracking: Visual progress indicators and achievement system
- Continuous Improvement: AI learns your preferences and adapts accordingly
VITE_GEMINI_API_KEY=your_google_gemini_api_keynpm run dev # Development server with hot reload
npm run build # Production build
npm run preview # Preview production build
npm run lint # Code quality checks// Example: Creating a specialized tutor
const customTutor = {
name: "Career Coach Sarah",
role: "Professional Interview Specialist",
personality: "confident",
traits: ["supportive", "professional", "detailed"],
expertise: ["interview skills", "workplace communication", "resume writing"],
emotionalTone: "encouraging"
};- β Voice-first design for visual impairments
- β Keyboard navigation support
- β High contrast color schemes
- β Screen reader compatibility
- β Multiple input methods (voice, text, touch)
- π Global Reach: Supports learners worldwide with internet access
- π Free Access: No subscription fees or premium barriers
- π Safe Space: Private, judgment-free learning environment
- π― Personalized: Adapts to individual learning needs and pace
- π± Device Agnostic: Works on any modern device with web browser
- Skill Development: Grammar, pronunciation, vocabulary, conversation fluency
- Confidence Building: Safe practice environment reduces anxiety
- Career Advancement: Professional communication skills training
- Cultural Integration: Real-world conversation practice for immigrants
We welcome contributions that enhance accessibility and educational impact:
- Fork the repository
- Create feature branch:
git checkout -b feature/accessibility-improvement - Commit changes:
git commit -m 'Add voice navigation for blind users' - Push to branch:
git push origin feature/accessibility-improvement - Open Pull Request with detailed description of social impact
- π Internationalization: Multi-language support
- βΏ Accessibility: Enhanced screen reader support
- π± Mobile Optimization: Improved mobile learning experience
- π Educational Content: Specialized learning modules
- π Privacy: Enhanced data protection features
- Lazy Loading: Components load on demand
- Efficient State Management: Context API with selective updates
- Optimized Builds: Vite's fast build system with tree shaking
- Caching Strategy: LocalStorage for offline capability
- β Chrome 90+ (Recommended for best voice features)
- β Firefox 88+
- β Safari 14+
- β Edge 90+
- Google Gemini AI: Latest v1.20.0 with streaming responses
- Speech Recognition: Web Speech API with fallback support
- Speech Synthesis: Cross-browser voice synthesis
This project is licensed under the MIT License - see the LICENSE file for details.
- π Privacy First: No personal data stored on external servers
- π Bias Mitigation: Inclusive training data and regular bias audits
- π€ Transparency: Open-source codebase for community review
- βοΈ Fair Use: Free access to educational AI technology
Project: English Tutor AI Category: AI for Social Good Impact: Democratizing English education worldwide through accessible, personalized AI tutoring
Key Differentiators:
- π― Direct Social Impact: Addresses real barriers to English learning
- π§ Technical Innovation: Advanced AI personality system with voice integration
- βΏ Accessibility Leadership: Voice-first design for inclusive learning
- π Global Scalability: Web-based platform reaching underserved communities
- π‘ Educational Innovation: Personalized AI tutors adapting to individual needs
Made with β€οΈ for a more connected, inclusive world
"Breaking language barriers, one conversation at a time."