Lie detection has gained importance and is now extremely significant in a variety of fields. It playsan important role in several domains, including law enforcement, criminal investigations, national security,workplace ethics, and personal relationships. As advances in lie detection continue to develop, real-timeapproaches such as voice stress technology have emerged as a feasible alternative to traditional methods such aspolygraph testing. Polygraph testing, a historical and generally established approach, may be enhanced or replacedby these revolutionary real-time techniques. Traditional lie detection procedures, such as polygraph testing, havebeen challenged for their lack of reliability and validity. Newer techniques, such as brain imaging and machinelearning, might offer better outcomes, although they are still in their early phases and require additional testing.This project intends to explore a deception-detection module based on sophisticated speech-stress analysistechniques that might be applied in a real-time deception system. The purpose is to study stress and otherarticulation cues in voice patterns, to establish their precision and reliability in detecting deceit, by building uponprevious knowledge and applying state-of-the-art architecture. The performance and accuracy of the system and itsaudio aspects will be thoroughly analyzed. The ultimate purpose is to contribute to the advancement of moreaccurate and reliable lie-detection systems, by addressing the limitations of old techniques and proposing practicalsolutions for varied applications. This paper proposes an efficient feature-selection strategy, which uses randomforest (RF) to select only the significant features for training when a real-life trial dataset consisting of audio filesis employed. Next, utilizing the RF as a classifier, an accuracy of 88% is reached through comprehensiveevaluation, thereby confirming its reliability and precision for lie-detection in real-time scenarios.