- 🎤 Voice Command Recognition
- ⌨️ Text Command Input
- 🌐 Quick Website Access (Google, YouTube, ChatGPT, etc.)
- 🕐 Time & Date Functions
- 📚 Wikipedia Search
pip install pyttsx3
pip install SpeechRecognition
pip install wikipedia
pip install pyaudioWindows:
pip install pipwin
pipwin install pyaudioLinux/Mac:
sudo apt-get install portaudio19-dev python3-pyaudio
pip install pyaudiopython jarvis_ui.py- "Wikipedia [topic]" - Search Wikipedia
- "Open YouTube" - Opens YouTube
- "Open Google" - Opens Google
- "Open ChatGPT" - Opens ChatGPT
- "What's the time" - Tells current time
- "What's the date" - Tells current date
- "Open LinkedIn" - Opens LinkedIn
- "Open Instagram" - Opens Instagram
- "Open WhatsApp" - Opens WhatsApp Web
- "Open Gmail" - Opens Gmail
- "Exit/Quit/Bye" - Closes the assistant
- Voice Command Button - Click and speak your command
- Type Command Button - Type your command manually
- Quick Actions - One-click buttons for common tasks
- Chat Display - Shows conversation history
- Status Indicator - Shows current status (Ready/Listening/Processing)
- Speak clearly when using voice commands
- Wait for "Listening..." status before speaking
- Use Type Command if voice recognition isn't working
- Try Quick Actions for instant results
- Check the chat display for responses
- Check microphone permissions in system settings
- Try using "Type Command" instead
- Install PyAudio properly using steps above
- Ensure speakers are on
- pyttsx3 should work offline
- Check system audio settings
Make sure all libraries are installed:
pip install -r requirements.txt- Change voice: Modify
self.engine.setProperty('voice', voices[1].id)- Use voices[0] for male voice
- Use voices[1] for female voice
- Change colors: Edit hex color codes in the UI section
- Add more commands: Add elif conditions in
process_command()method