We built an open-source project Starmoon and are using affordable hardware components to bring AI characters to real-word objects like toys and plushies (or even your talking fridge). With voice to voice models sounding more and more human every day, a cool use-case would be to take the conversation away from screens and personify real-world objects. For our project we use an ESP32-S3 microcontroller with a mic and a mono-speaker to keep the cost at $10. We are fully open-sourcing our frontend, backend and firmware so you too can get started and create and customize your companion device. Appreciate any feedback below, it will help us improve :)