How It Works
PageParrot is powered by a Raspberry Pi Zero 2 W single-board computer and a USB webcam. It runs a Python script that waits for a button press, then snaps a picture of the book with the webcam. The image is then sent to Google’s Gemini 2.5 Flash large language model, along with a prompt instructing it to tell me all the text contained in the image. The text it returns is then fed into Piper to synthesize speech, which is played on a Bluetooth speaker.
Media
Bill of Materials
- 1 x Raspberry Pi Zero 2 W
- 1 x USB webcam
- 1 x Bluetooth speaker
- 1 x Push button
- Aluminum extrusions, wire, twist ties, and hot glue
About the Author
This is great, i'm looking at making a device that can read LED displays (i.e. on microwaves) for low vision/blind users. Do you have advice if this is adaptable for that?