Music genre classification is a critical task in the digital age, essential for various applications such as personalized playlists and music recommendation systems. Among various machine learning algorithms, the K-Nearest Neighbors (KNN) algorithm has emerged as a robust technique due to its simplicity and adaptability. This paper explores the application of the KNN algorithm in music genre classification, delving into diverse feature extraction methods, distance metrics, and the impact of different K values on classification performance. Comparisons with other popular algorithms highlight the efficacy and potential of KNN in real- world music classification applications