The accurate diagnosis of voice disorders and laryngeal conditions plays a crucial role in the effective treatment and management of patients’ health. This paper discusses advanced classification techniques aimed at enhancing the diagnostic process for voice disorders and laryngeal conditions. Leveraging state-of-the-art machine learning techniques, this study aims to improve the accuracy of vocal disorder classification. It focuses on dysphonia and investigates a number of machine learning techniques in order to identify the most effective algorithm for diagnosing aberrant voices in comparison to normal voices. Through the use of the Saarbruecken Voice Database dataset, the research investigates various algorithms, including Random Forest and Support Vector Machine, and rates them according to F1-score, sensitivity, specificity, and accuracy. As stated in the report, these methodologies have the potential to significantly enhance the diagnostic process as well as the monitoring of voice dysfunction.