An AI-first React Native app designed to help users improve their English speaking skills through interactive conversations, pronunciation practice, and vocabulary building.
- Real-world conversations: Practice ordering coffee, checking into hotels, shopping, and more
- Progressive difficulty: Beginner, intermediate, and advanced levels
- Audio playback: Native speaker pronunciations for each conversation
- Alternative responses: Learn multiple ways to express the same idea
- Hints and tips: Contextual guidance for better pronunciation
- Natural conversations: Chat with an AI assistant on various topics
- Adaptive responses: AI adjusts complexity based on your skill level
- Real-time feedback: Pronunciation scoring and improvement suggestions
- Multiple topics: Daily life, travel, work, culture, technology, and more
- Spaced repetition: Scientifically-proven learning algorithm
- Interactive cards: Flip cards with audio pronunciation
- Category filtering: Focus on specific vocabulary areas
- Progress tracking: Monitor your vocabulary mastery
- Audio support: Hear correct pronunciations for every word
- Speech recognition: Advanced pronunciation analysis
- Detailed feedback: Get scores for accuracy, fluency, and completeness
- Phoneme analysis: Word-by-word pronunciation breakdown
- Haptic feedback: Physical feedback for pronunciation quality
- Progress tracking: Monitor improvement over time
- Achievement system: Unlock badges and celebrate milestones
- Daily streaks: Build consistent learning habits
- Study time tracking: Monitor your dedication and effort
- Pronunciation analytics: See your speaking improvement over time
- Vocabulary mastery: Track words learned and retention rates
- React Native: Cross-platform mobile development
- Expo: Development platform and build tools
- TypeScript: Type-safe JavaScript for better development
- React Navigation: Bottom tabs and stack navigation
- Restyle: Type-safe styling system
- React Native Reanimated: Smooth animations and transitions
- React Native Gesture Handler: Touch interactions
- Expo AV: Audio playback and recording
- Expo Speech: Text-to-speech functionality
- Speech recognition: Pronunciation analysis (mockup with real API integration ready)
- AsyncStorage: Local data persistence
- Custom storage service: User progress and preferences
- Spaced repetition algorithm: Optimized flashcard scheduling
- Expo Haptics: Physical feedback for interactions
- React Native Progress: Visual progress indicators
- Custom vector icons: Emoji-based navigation icons
src/
├── components/ # Reusable UI components
│ ├── Box.tsx # Styled container component
│ ├── Text.tsx # Styled text component
│ ├── Button.tsx # Interactive button component
│ ├── Flashcard.tsx # Flip card for vocabulary
│ ├── PronunciationPractice.tsx # Speech recording & analysis
│ └── AIConversation.tsx # AI chat interface
├── screens/ # Main app screens
│ ├── HomeScreen.tsx # Scenario selection
│ ├── ScenarioScreen.tsx # Conversation practice
│ ├── FlashcardScreen.tsx # Vocabulary review
│ ├── AIConversationScreen.tsx # AI chat setup
│ └── ProfileScreen.tsx # Progress tracking
├── navigation/ # App navigation setup
│ └── AppNavigator.tsx # Tab and stack navigation
├── services/ # Business logic and APIs
│ ├── StorageService.ts # Data persistence
│ ├── AudioService.ts # Audio playback/recording
│ └── SpeechService.ts # TTS and speech analysis
├── data/ # Static data and content
│ ├── scenarios.ts # Conversation scenarios
│ ├── flashcards.ts # Vocabulary cards
│ └── achievements.ts # Gamification system
├── theme/ # Design system
│ └── theme.ts # Colors, spacing, typography
└── types/ # TypeScript interfaces
└── index.ts # App-wide type definitions
The app provides realistic conversation scenarios that users might encounter in English-speaking environments:
- Cafe ordering: Practice food and drink vocabulary
- Airport check-in: Learn travel-related phrases
- Hotel booking: Master hospitality conversations
- Shopping: Navigate retail interactions
- Restaurant dining: Handle food service situations
Each scenario includes:
- Audio examples from native speakers
- User pronunciation practice
- Alternative response suggestions
- Contextual hints and tips
- Progressive difficulty levels
The AI conversation feature simulates natural dialogue:
- Topic selection: Choose from 8+ conversation topics
- Skill-level adaptation: Beginner, intermediate, and advanced responses
- Natural flow: AI responds contextually to user input
- Pronunciation integration: Practice speaking within conversations
- Progress tracking: Monitor conversation frequency and quality
Vocabulary learning through spaced repetition:
- 20+ initial flashcards across multiple categories
- Adaptive scheduling: Cards appear based on difficulty and retention
- Audio pronunciation: Hear correct word pronunciations
- Visual design: Attractive flip-card animations
- Progress tracking: Monitor vocabulary mastery levels
Track learning across multiple dimensions:
- XP and levels: Gamified progression system
- Achievement badges: 14 different accomplishments to unlock
- Daily streaks: Encourage consistent practice
- Pronunciation analytics: Track speaking improvement
- Vocabulary metrics: Monitor word learning and retention
- Study time tracking: See total learning investment
-
Clone the repository
git clone https://github.com/your-username/ai-better-speaking-english.git cd ai-better-speaking-english -
Install dependencies
npm install # or yarn install -
Start the development server
npx expo start
-
Run on device
- iOS: Press
iin terminal or scan QR code with Camera app - Android: Press
ain terminal or scan QR code with Expo Go app
- iOS: Press
The app is designed to work with MP3 audio files for realistic pronunciation practice. Audio files should be placed in assets/audio/ directory:
cafe-welcome.mp3cafe-pastries.mp3airport-checkin.mp3hotel-greeting.mp3- And more...
Note: Current implementation includes placeholders. Replace with actual recorded audio files from native English speakers.
The app includes a mock speech recognition system. For production use, integrate with:
- Google Cloud Speech-to-Text
- Azure Cognitive Services Speech
- AWS Transcribe
- Apple Speech Framework (iOS)
- Android SpeechRecognizer (Android)
- Update
src/data/scenarios.ts - Add conversation flows with audio references
- Include vocabulary and grammar points
- Set appropriate difficulty levels
- Extend
src/data/flashcards.ts - Include definitions, examples, and audio references
- Set categories and difficulty levels
- Update spaced repetition parameters
- Modify
src/data/achievements.ts - Define unlock conditions and rewards
- Add icons and descriptions
- Update progress checking logic
- Video conversations: Practice with video scenarios
- Group conversations: Multi-person dialogue practice
- Voice recognition: Real-time speech-to-text integration
- Custom scenarios: User-generated conversation practice
- Social features: Share progress with friends
- Offline mode: Practice without internet connection
- Accent training: Region-specific pronunciation practice
- Grammar exercises: Dedicated grammar practice modules
- Fork the repository
- Create a feature branch (
git checkout -b feature/amazing-feature) - Commit your changes (
git commit -m 'Add amazing feature') - Push to the branch (
git push origin feature/amazing-feature) - Open a Pull Request
Pierre-Henry Soria. A super passionate engineer who loves automating content creation efficiently!
Enthusiast of YouTube, AI, learning, and writing! Find me at pH7.me
Enjoying this project? Buy me a coffee (spoiler: I love almond extra-hot flat white coffees).
This project is licensed under the MIT License - see the LICENSE file for details.
Happy Learning! 🎉 Improve your English speaking skills with AI-powered practice!