iTest is an interactive educational application designed to help Arabic-speaking children practice spoken Hebrew in a simple and engaging way.

The system allows users to record spoken sentences in Hebrew, which are then automatically transcribed using speech-to-text technology. The transcribed text is analyzed by an AI model that provides immediate, personalized, and encouraging feedback, focusing on grammar, pronunciation, and sentence structure.

The main goal of the project is to create a “virtual teacher” that helps children improve their Hebrew speaking skills through real-time interaction and positive reinforcement.

The system is built as a rapid MVP using Python and Streamlit, integrates AI services for speech recognition and language analysis, and stores user interactions in a MongoDB database for future learning and analysis.