If you grew up either playing or watching Pokémon, you may have wondered what it would be like to use a Pokédex in real life. Now, thanks to Abe's Projects' latest creation, you can! This custom-built Pokédex works just like the original, for the most part, thanks to a little help from Chat GPT.
According to Abe, the goal was to recreate the fictional user experience as much as possible. It needed to not only look like a Pokédex, but also function as one. We might not live in a world with actual Pokémon, but we do live in a world with fictional Pokémon. Instead of recognizing creatures, this Pokédex can be trained to recognize images and figurines of Pokémon and relay information about them using text-to-speech.
The Pokédex shell used to house the hardware was 3D-printed and designed by Abe just for this project. Abe wanted the Pokédex to sound as much like the original as possible and decided to use PlayHT to clone the voice used in the Pokémon anime series. The results might not be perfect, but it's close enough to satisfy your inner trainer.
The board driving the whole operation is a Seed Studio Xiao ESP32S3 Sense. It's connected to a camera module, which is crucial to the functionality of the Pokédex. The camera is used to capture images of Pokémon which are then parsed through Chat GPT to see which Pokémon it is. Once the Pokémon is identified, the data is checked against a huge Pokémon database, via PokéAPI, which provides the Pokédex with a detailed description of the detected Pokémon.
If you want to get a closer look at this custom Pokédex in action, check out the video shared by Abe to his official YouTube channel, Abe's Projects.
Stay on the Cutting Edge
Join the experts who read Tom's Hardware for the inside track on enthusiast PC tech news — and have for over 25 years. We'll send breaking news and in-depth reviews of CPUs, GPUs, AI, maker hardware and more straight to your inbox.
Ash Hill is a Freelance News and Features Writer at Tom's Hardware US. She manages the Pi projects of the month and much of our daily Raspberry Pi reporting.