A comprehensive voice-controlled desktop assistant built with Python that responds to voice commands and automates various computer tasks through speech recognition and text-to-speech technology.
- Voice Recognition: Responds to natural voice commands in English.
- Text-to-Speech: Provides audio feedback with customizable voice options.
- Web Automation: Opens websites, performs Google/YouTube searches.
- Application Control: Launches apps like VS Code, WhatsApp, Discord, Spotify, etc.
- System Management: Clears temp files, manages Recycle Bin.
- Email Integration: Automated email sending through Gmail.
- Music Control: Spotify playlist management and playback.
- Wikipedia Integration: Fetches and reads Wikipedia summaries.
- Time & Weather: Real-time information and weather reports.
- Sound Effects: Interactive audio feedback for enhanced user experience.
- Python 3.6+
- speech_recognition - Voice command processing
- pyttsx3 - Text-to-speech conversion
- pyautogui - GUI automation and control
- webbrowser - Web browser automation
- wikipedia - Wikipedia API integration
- datetime - Time and date management
- winsound - Sound effects playback
- os - System operations
Before running SCAI, ensure you have:
- Python 3.6 or higher installed
- Working microphone for voice input
- Internet connection for web-based features
- Windows OS (for certain system-specific features)
- Clone the repository
git clone https://github.com/pingakshgaur/Desktop-Assistant-SCAI.git
cd Desktop-Assistant-SCAI- Install required packages
pip install pyautogui
pip install pyttsx3
pip install speechrecognition
pip install wikipedia
pip install webbrowser
pip install pyaudio- Setup microphone permissions (if required by your OS)
- Run the assistant
python scai-d.py- Voice Commands Examples:
- "Hey SCAI" - Basic greeting.
- "Open YouTube" - Opens YouTube in the default browser.
- "Search Google for Python tutorials" - Performs a Google search.
- "What's the time?" - Tells the current time.
- "Play my Spotify playlist" - Opens Spotify.
- "Tell me about Albert Einstein" - Wikipedia search.
- "Clear temporary files" - System cleanup.
- "Sleep for 30 seconds" - Pause assistant.
- "Exit" - Close the assistant.
Desktop-Assistant-SCAI/
│
├── da-SCAI.py # Main assistant script
├── SFX/... # Sound effects folder
├── README.md # Project documentation
└── REQUIREMENTS.md # Python dependencies
- Change voice gender by modifying
bot_voicevariable (0 for DAVID, 1 for ZIRA). - Adjust speech rate in the voice setup section (1 to 200).
- Modify volume levels as needed (1 to 100).
Update file paths in the code for your system:
vscode_path = "C:\\Your\\Path\\To\\VS Code\\Code.exe"
spotify_path = "C:\\Your\\Path\\To\\Spotify\\Spotify.exe"Contributions are welcome! Please feel free to submit a Pull Request. For major changes:
- 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
- Add machine learning for better voice recognition
- Multi-language support
- Custom command creation interface
- Bugs fix & minor changes
- Some features may require specific application versions.
- Microphone sensitivity may need adjustment based on hardware or physical environment.
- Path configurations need manual setup for different systems.
This project is not licensed under any company or individual and is Free for anyone to use/modify.
Pingaksh Gaur
- GitHub: @pingakshgaur
- LinkedIn: Pingaksh Gaur
- Email: pingakshgaur@gmail.com
- Thanks to the Python community for excellent libraries.
- Inspired by AI assistants like JARVIS and Alexa.