Developed a full-stack language learning application tailored for Luxembourgish, combining speech recognition, natural language understanding, and generative AI. Fine-tuned OpenAI’s Whisper model for accurate Luxembourgish transcription and built a custom text-to-speech (TTS) engine for realistic audio feedback. A RAG-based architecture enables the app to answer user queries contextually, making learning highly interactive. The frontend is built with React, while Flask powers the backend. Designed to deliver an immersive, conversation-driven auditory learning experience.