Real-time hand sign language recognition systems present a groundbreaking approach to enriching human-computer interaction, especially benefiting the deaf and mute communities. This abstract outlines a novel system leveraging computer vision and machine learning advancements to detect and interpret signs instantly. By employing sophisticated algorithms, the system effectively tracks and recognizes hand movements, enabling seamless interaction with digital devices. Machine learning enables the classification and interpretation of hand sign language. The research paper aims to develop a real-time hand sign language recognition system using a live camera feed, serving as a crucial communication tool for the deaf and mute community and fostering natural interaction with technology. The proposed model is based on the deep neural network (LSTM) model. This model integrates an American Sign Language-based system, boasting 98% accuracy. It addresses the challenges faced by individuals with hearing and speaking impairments to enhance accessibility and usability, bridge communication gaps, and foster inclusivity in the digital era.