Step One: Camera
- This camera is an AGFA Synchro Box from the 50's. Any camera/device will do, as long as a Raspberry Pi, Powerbank and Pi Camera fit inside.
Step Two: Electronics
- The electronics are straightforward. To start off, set up the Pi and connect the Pi Camera. To power, connect the powerbank, the same way a user would with their phone.
- When everything is wired up, start on the fiddly part, placing the camera. This project kept the shutter open and made sure it was aligned. This step takes some time.
- All that remains is to plug in in the user’s headphones and make sure the Pi plays audio via the 3.5mm jack.
Step Three: Code
- The code is tricky, but to make things easy, here is a high level overview:
- Take a picture every second.
- Check that the picture is mostly black (shutter is closed). If so, delete the picture
- If not, send the picture to the AI API, receiving the caption back.
- This caption is turned into an MP3 file, playing it via the headphones.
Step Four: Result
- Now the user has a camera that doesn't take pictures, it only captions them.