In today’s world people are fond of music, there is multiple set of genres present in our musical app playlist. There is a recommendation system used by companies to make a set of songs into one album. It needs an efficient algorithm to classify the records. The purpose of the music genre classification is to categorize songs or audio files according to a range of characteristics into the appropriate genre. This study explores the utilization of machine learning approaches for music genre classification using the well-known GTZAN dataset. The objective of this project is to create a reliable model that can identify the genre of any music with accuracy. Songs are categorized according to their respective genres using features that are extracted from audio files, such as chroma, spectral bandwidth, spectral contrast, mel-frequency cepstral coefficients (MFCCs), and zero crossing rate. The prominent machine learning models such as Support Vector Machines (SVM), k-Nearest Neighbor (k-NN), and Random Forest are implemented to classify the songs and their results are compared to determine which machine learning model is best for genre categorization. These models are enhanced with GridSearchCV Optimization technique.