This study explores the use of formant features (F1, F2, and F3) for gender classification of speakers using machine learning techniques. The primary objective was to assess the ability of these acoustic features to distinguish between male and female voices and to evaluate the performance of two widely used classifiers, the Multilayer Perceptron (MLP) and Support Vector Machine (SVM). A dataset comprising speech recordings from 77 participants (37 male and 40 female) was analyzed, with vowel segments /a/, /i/, and /u/ selected for formant extraction. The formants were computed using linear predictive coding coefficients, and the extracted features were projected onto the (F1, F2) plane to visualize the phonetic differences between genders. The results revealed that male speakers' vowels are positioned slightly to the right in the formant space, while female speakers' vowels occupied a larger area, forming a more expansive triangle. This phonetic difference between male and female speakers is crucial for gender classification tasks. The classifiers were then evaluated using the F-measure, a metric that combines precision and recall. The results showed that the F-measure for the MLP classifier was 2% higher than that for the SVM (82% and 80% respectively), suggesting a slightly better performance of MLP in gender classification when formant features (F1, F2, and F3) are used. This indicates that MLP is more effective in distinguishing male and female speakers based on their vowel formants. These findings also underscore the potential of formant-based features for building accurate gender recognition systems. The study also highlights the utility of machine learning techniques, particularly MLP, in analyzing phonetic data and providing insights into speaker classification.