This study presents a comparative analysis of Artificial Neural Networks (ANNs) and Support Vector Machines (SVMs) for speaker classification tasks, focusing on their performance metrics, computational efficiency, and adaptability to diverse datasets. The research utilized public datasets and volunteer recordings to train models using x-vector embeddings extracted via the SpeechBrain encoder. As for models evaluation, precision, recall, F1-score, and accuracy were used. Results show that both ANNs and SVMs achieve good robustness in dealing with class imbalance and the overall accuracy for the SVMs (97%) is only marginally better than that for ANNs (96%). Using parameter tuning, this study shows the computation speed of SVMs and the flexibility of ANNs and provides some insight into how to choose models in speaker classification applications.