ahmedelbrawany/A.Eye ? reverse-engineered prompt

Build me a Python project for a Raspberry Pi that works like an artificial eye for blind and visually impaired users.

It should use the camera and voice commands to let the user switch between different modes like detecting objects, recognizing faces, reading text out loud, and identifying Egyptian money. When something is found, it should speak the result clearly with text to speech, including simple details like object name and distance if possible. I want it to work offline as much as possible, so please use local speech recognition and local AI tools instead of depending on the internet.

Make it feel like a real standalone device, with a simple main menu or command flow that is easy to use by voice. If you need to look up current docs online for any libraries, do that. Please organize the code so the different features are separated but still work together cleanly from one main entry point.