This project demonstrates the integration of the ESP32 with
Google Gemini AI to create an interactive AI-powered assistant.
The ESP32 sends user input to the Gemini API, receives intelligent responses,
and then converts them into natural-sounding speech using Text-to-Speech (TTS).
The system combines AI conversation with real-time audio output, allowing users to experience voice-based interaction without needing a computer or cloud-heavy setup. It works as a lightweight, portable smart assistant built on embedded hardware.
Potential applications include smart home voice assistants, accessibility tools for visually impaired users, educational companions, and IoT devices that respond with speech. The project highlights the capability of ESP32 to handle modern AI-driven tasks and merge them with practical hardware applications.