Communication skills are crucial for success in many fields and industries, especially those requiring public speaking. However, many people find public speaking to be a challenging and anxiety-inducing task. To address this, we aim to develop a user-friendly personalised tool to help individuals with their public speaking skills by utilising computer vision and speech recognition technologies. The purpose of this study is to judge an individual’s public speaking abilities by analysing video footage of the individual. The analysis focuses on three main elements: voice, speech and body language of the user. Features such as facial expressions, hand gestures, posture, and auditory parameters like disfluencies are extracted and assessed. Individuals can thus receive insights on their skills tailored to their needs and use them to enhance their public speaking and build confidence in their speech over time.