Music plays a prominent role in various aspects of human life, culture, and society by influencing emotions, strengthening social bonds, preserving traditions, and shaping personal and collective identities. As AI emerges as a powerful tool to automate various tasks, music recommendation systems have become an integral part of this transformation. These systems automatically generate personalized music playlists for users based on their mood and listening behavior. By analyzing factors like facial expressions, voice tone, text input, and listening history, AI-driven music recommendation systems identify the user’s emotional state and suggest songs that match or enhance their mood. Emotion-based music recommendation systems significantly enhance the way people experience music by improving emotional well-being, boosting user engagement, and broadening musical preferences. In this work, we propose an application called EMUS, an intelligent music recommendation system designed to suggest music based on the user’s emotional state.