This project focuses on identifying and distinguishing between authentic audio recordings and those that have been artificially generated or manipulated. As voice cloning technology advances, creating realistic audio deepfakes has become easier, raising concerns about misinformation and privacy. To combat this, this project aims to develop machine learning models to analyse audio features such as pitch, tone, cadence, and spectral characteristics. These techniques are implemented to detect subtle anomalies that may indicate manipulation, even in high-quality deepfake audio. Additionally, training on large and diverse datasets that include both genuine and synthetic voices allows these models to improve their accuracy and robustness. Apart from proposing and implementing deep learning methods for detection purposes, this project also involves collecting and/or generating different datasets for experiments.