Skip to content

DaveRucha/AirSlides

Repository files navigation

🖐️ AirSlides – Gesture-Controlled Slide Narration System

AirSlides is a real-time, contactless presentation tool that lets you control slides and narrate them using only hand gestures — no remotes, no clicking, no touching.

Built using Python, OpenCV, Mediapipe, and gTTS, it enables a fully hygienic and intuitive presentation experience.


🚀 Features

Gesture Action
✋ Palm Next Slide
✌️ V Sign Previous Slide
☝️ Point Toggle Pointer (red dot)
👌 OK Sign Toggle Draw Mode (whiteboard)
🤘 Rock Sign Clear Drawing
🤙 L Sign Toggle Slide Narration

🎤 Narration is powered by:

  • OCR using pytesseract
  • Text-to-Speech using gTTS + pygame.mixer

🛠 Installation

  1. Install Python 3.8 to 3.11 from https://www.python.org/downloads/

  2. Install required Python packages:

pip install -r requirements.txt
  1. Install Tesseract OCR:

  2. Install Poppler for Windows (for PDF conversion):


▶️ How to Run

  1. Launch the app:
python airslides.py
  1. When prompted, enter the path to a PDF file of your slides.

  2. Use hand gestures in front of your webcam to:

    • Navigate slides
    • Draw and highlight
    • Narrate the slide content out loud

💡 Why AirSlides?

  • ✅ 100% Touchless
  • ✅ Real-time OCR and narration
  • ✅ Works offline (no internet required)
  • ✅ Great for educators, demos, recordings

📦 Requirements

  • Python 3.8–3.11
  • Webcam
  • Tesseract OCR
  • Poppler
  • Python packages:
    • opencv-python
    • mediapipe
    • pytesseract
    • gTTS
    • pygame
    • pdf2image
    • Pillow
    • pywinauto

👤 Author

Created by Rucha Avinash Dave

About

Gesture-based slide controller with real-time narration (Python, OpenCV, Mediapipe, gTTS)

Topics

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages