A simple but powerful Python tool that lets you select any area on your screen, capture it instantly, and send it to Google Gemini along with your custom prompt for real-time AI analysis.
This tool is built for anyone who wants fast, on-demand screenshot understanding — OCR, UI debugging, object detection, code extraction, visual explanations, and more.
When you run the program:
- A translucent overlay appears on your screen.
- Your cursor changes to a crosshair for precision.
- You click and drag to select the area you want to capture.
- The selected image is immediately sent to Gemini AI with your prompt.
- The AI's response is returned instantly.
No clutter. No extra steps. Just select → analyze → done.
Open the main file and replace the placeholder:
genai.configure(api_key="YOUR_API_KEY_HERE")