Digital Assistant with Voice & Intelligent Decisions
Advanced AI Assistant with Voice Control, Gesture Recognition, and Complete Device Management
Developed by Nexuzy Tech Ltd.
Features • Installation • Usage • Contributing • Support
- 🎙️ Voice Control - Hands-free device control via natural voice commands
- ✋ Gesture Recognition - Control your device with hand gestures via camera
- 💬 AI Chat - Intelligent conversations with on-device AI models
- 👁️ Vision Processing - Image recognition and visual understanding
- 🌍 Multi-Language - Support for 15 languages including all major Indian languages
- 📡 Offline First - All processing happens locally on your device
Control everything with your voice:
- Device Control: WiFi, Bluetooth, Location, Flashlight on/off
- Volume Control: Increase, decrease, mute, set specific level
- Communication: Make calls, send SMS, send emails
- Media Control: Play, pause, next, previous, forward, rewind
- Camera: Take selfie, record video
- Apps: Open any app by voice
- Information: Time, date, weather, alarms
- System: Lock device, take screenshot
- Voice Typing: Type in any app using voice
Supported Gestures:
- ✋ Open Palm - Show pointer
- ✊ Closed Fist - Hide pointer
- ☝️ Pointing Up - Move pointer
- ✌️ Victory Sign - Click action
- 👍 Thumbs Up - Confirm
Mouse-Like Pointer:
- Floating overlay pointer
- Smooth movement animation
- Visual feedback (glow effects)
- Click animations
15 Languages Total:
- 🇬🇧 English (default)
- 🇮🇳 Hindi (हिन्दी)
- 🇮🇳 Tamil (தமிழ்)
- 🇮🇳 Telugu (తెలుగు)
- 🇮🇳 Bengali (বাংলা)
- 🇮🇳 Marathi (मराठी)
- 🇮🇳 Gujarati (ગુજરાતી)
- 🇮🇳 Kannada (ಕನ್ನಡ)
- 🇮🇳 Malayalam (മലയാളം)
- 🇮🇳 Punjabi (ਪੰਜਾਬੀ)
- 🇮🇳 Odia (ଓଡ଼ିଆ)
- 🇮🇳 Urdu (اردو)
- 🇮🇳 Sanskrit (संस्कृतम्)
- 🇮🇳 Kashmiri (कॉशुर)
- 🇮🇳 Assamese (অসমীয়া)
- Tiny (75MB) - For 1-2GB RAM devices
- Base (142MB) - For 2-3GB RAM devices
- Small (466MB) - For 3GB+ RAM devices
- TinyLlama (669MB) - Lightweight chat model
- Qwen 1.5 (1.1GB) - Advanced conversational AI
- Phi-2 (1.6GB) - Microsoft's powerful model
- MobileNetV2 (14MB) - Lightweight image recognition
- ResNet50 (98MB) - Advanced image classification
- Hand Landmarker (25MB) - 21-point hand tracking
- Gesture Recognizer (31MB) - Gesture classification
- Universal Sentence Encoder (50MB per language)
The app automatically selects appropriate models based on your device's RAM:
- 1-2GB RAM: Tiny voice + Light chat + Lite vision (~914 MB)
- 2-4GB RAM: Base voice + Standard chat + Standard vision (~1.6 GB)
- 4GB+ RAM: Small voice + Pro chat + Standard vision + All languages (~2.7 GB)
Your Privacy is Our Top Priority
✅ All data stored locally on YOUR device ✅ No data sent to external servers ✅ No user tracking or analytics ✅ No personal information collected ✅ No account required ✅ No cloud storage
- Voice recordings: Processed locally
- Camera images: Processed locally
- AI models: Downloaded and stored locally
- Chat history: Stored locally
- Settings: Stored locally
Complete privacy policy: PRIVACY_POLICY.md
- Android 8.0 (API 26) or higher
- Minimum 1GB RAM (2GB+ recommended)
- Camera for gesture control
- Microphone for voice commands
- 500MB-3GB storage for AI models (depends on device)
-
Download the APK:
- Go to Releases
- Download the latest APK
-
Install the App:
- Enable "Install from Unknown Sources" in settings
- Open the APK and install
-
Grant Permissions:
- Camera (for gesture control)
- Microphone (for voice commands)
- Storage (for AI models)
- Other permissions as needed
-
Download Models:
- First launch will auto-download models
- Models selected based on your device RAM
- Takes 2-5 minutes depending on device
- Launch D.A.V.I.D AI
- Wait for model downloads to complete
- Grant all required permissions
- Say "Hey David" to activate voice control
- Or use hand gestures for pointer control
- Android Studio Hedgehog or later
- Kotlin 1.9.0+
- Gradle 8.0+
- Android SDK 34
- JDK 17+
# Clone the repository
git clone https://github.com/david0154/david-ai.git
cd david-ai
# Clean build
./gradlew clean
# Build debug APK
./gradlew assembleDebug
# Build release APK
./gradlew assembleRelease
# Install on connected device
./gradlew installDebug- Debug:
app/build/outputs/apk/debug/app-debug.apk - Release:
app/build/outputs/apk/release/app-release.apk
- Privacy Policy
- Complete Fixes Documentation
- Android Studio Setup Guide
- GitHub Wiki
- API Documentation (coming soon)
- Contributing Guidelines (coming soon)
- Email: david@nexuzy.in
- GitHub Issues: Create an issue
- GitHub Discussions: Join discussions
Found a bug? Report it here
Please include:
- Device model and Android version
- RAM size
- Steps to reproduce
- Expected vs actual behavior
- LogCat output (if possible)
- Screenshots (if applicable)
Have an idea? Request a feature here
Please describe:
- The feature you'd like
- Why it would be useful
- How it should work
- Any examples or mockups
We welcome contributions! Whether it's:
- 🐛 Bug fixes
- ✨ New features
- 📝 Documentation improvements
- 🌍 Translations
- 🎨 UI/UX enhancements
- Fork the repository
- Create your feature branch (
git checkout -b feature/AmazingFeature) - Commit your changes (
git commit -m 'Add some AmazingFeature') - Push to the branch (
git push origin feature/AmazingFeature) - Open a Pull Request
Please read our Contributing Guidelines (coming soon) for details.
Thanks to all contributors who have helped make D.A.V.I.D AI better!
Want to see your name here? Start contributing!
 David Creator & Lead Developer 💻 💡 👁 📖 |
Nexuzy Tech Ltd. Company & Support 🏢 📧 🔒 🚀 |
Roles:
- 💻 Code
- 💡 Ideas & Planning
- 👁 Review
- 📖 Documentation
- 🏢 Company/Organization
- 📧 Support
- 🔒 Security & Privacy
- 🚀 Deployment
|
Lead Developer & Creator
About:
Contributions:
Skills:
Contact:
|
To all users who:
- 🐛 Report bugs and issues
- 💡 Suggest features and improvements
- ⭐ Star the project
- 📢 Share with others
- 🌍 Contribute translations
- 📝 Improve documentation
- 🤝 Spread the word
Your support makes D.A.V.I.D AI better every day!
- ✅ Voice Control - COMPLETE
- ✅ Gesture Recognition - COMPLETE
- ✅ AI Chat - COMPLETE
- ✅ Multi-Language Support - COMPLETE
- ✅ Device Control - COMPLETE
- ✅ Privacy-First Design - COMPLETE
- 🚧 Advanced Vision Features - IN PROGRESS
- 📋 Smart Home Integration - PLANNED
- 📋 Wearable Support - PLANNED
- Enhanced gesture recognition
- More voice command types
- Custom wake word training
- Gesture customization
- Smart home device control
- Calendar integration
- Email management
- Note taking
- AR features
- Wearable app
- API for third-party apps
- Cloud sync (optional)
This project is licensed under the MIT License - see the LICENSE file for details.
Copyright © 2026 Nexuzy Tech Ltd.
Brand: D.A.V.I.D AI
Developer: Nexuzy Tech Ltd.
Lead Developer: David (@david0154)
- Language: Kotlin
- UI Framework: Jetpack Compose
- AI Models:
- Whisper (Speech Recognition)
- LLaMA/Phi-2 (Chat)
- ONNX (Vision)
- MediaPipe (Gesture)
- Architecture: MVVM
- Dependency Injection: Hilt (planned)
- Database: Room (for chat history)
- Networking: OkHttp + Retrofit
D.A.V.I.D AI is developed and maintained by Nexuzy Tech Ltd., a company focused on building privacy-first AI applications that empower users without compromising their data.
To create powerful AI tools that:
- Respect user privacy
- Work offline-first
- Are accessible to everyone
- Put users in control
🔒 Privacy First: No data collection, ever
🌍 Inclusive: 15 languages, accessible to all
📡 Offline First: Works without internet
🔓 Open: Transparent development
💚 User-Focused: Built for real people
- Email: david@nexuzy.in
- GitHub: @david0154
- Website: Coming soon
If you find D.A.V.I.D AI useful, please consider:
- ⭐ Star this repository
- 🐛 Report bugs via issues
- 💡 Suggest features via feature requests
- 📢 Spread the word - Share with friends and colleagues
- 🤝 Contribute - Submit a pull request
- OpenAI Whisper - Voice recognition models
- HuggingFace - LLM models (TinyLlama, Qwen, Phi-2)
- ONNX - Vision models
- Google MediaPipe - Gesture recognition
- TensorFlow - Language models
- All open-source contributors
- Our amazing users and community
Made with ❤️ by Nexuzy Tech Ltd.
© 2026 Nexuzy Tech Ltd. All rights reserved.
Privacy-First AI • Your Device, Your Data • No Data Collection
D.A.V.I.D AI is a trademark of Nexuzy Tech Ltd.