Skip to content

Mohan18R/virtual-assistant

Folders and files

NameName
Last commit message
Last commit date

Latest commit

Β 

History

5 Commits
Β 
Β 
Β 
Β 
Β 
Β 

Repository files navigation

Virtual Assistant

An intelligent AI assistant that combines voice recognition and hand gesture control to perform system automation, open applications, search the web, and control media playback hands-free.

πŸš€ Features

  • Voice-Controlled AI Assistant: Uses SpeechRecognition and pyttsx3 for natural language interactions.
  • Gesture-Based System Control: Utilizes OpenCV and MediaPipe to detect hand gestures for controlling volume, media playback, and navigation.
  • Automated System Interactions: Integrates PyAutoGUI for executing commands triggered by voice and gestures.
  • Wikipedia & Web Search: Fetches concise answers from Wikipedia or opens a Google search when needed.
  • Application Launcher: Opens installed applications like VS Code, Word, and web apps like YouTube and WhatsApp.

πŸ› οΈ Tech Stack

  • Python
  • SpeechRecognition
  • pyttsx3
  • OpenCV
  • MediaPipe
  • PyAutoGUI
  • Wikipedia API

🎯 How It Works

1️⃣ Voice Commands

  • Say "Open VS Code" to launch VS Code.
  • Say "Search Python tutorials" to get results on Google.
  • Say "Gesture mode" to activate hand tracking.
  • Say "Silent mode" to stop voice responses.
  • Say "Wake up" to resume listening.

2️⃣ Hand Gestures (in Gesture Mode)

  • Move Cursor: Index finger up, all others down.
  • Click: Thumb up, all other fingers down.
  • Volume Control: Adjusts based on distance between fingers.
  • Swipe Left/Right: Moves slides/media using specific hand signs.
  • Take Screenshot: Perform a specific hand gesture.

πŸ—οΈ Installation

  1. Clone the repository
    git clone https://github.com/your-repo.git
    cd ai-assistant-gesture
  2. Install dependencies
    pip install -r requirements.txt
  3. Run the assistant
    python main.py

πŸ“Œ Future Enhancements

  • Context-aware voice responses
  • More refined hand gesture actions
  • GUI for better user experience

πŸ“œ License

This project is licensed under the MIT License.

🀝 Contributing

Feel free to fork, submit issues, and send pull requests!


About

No description, website, or topics provided.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

 
 
 

Contributors

Languages