The deaf and mute community faces significant challenges due to their in ability to communicate effectively, especially in areas with limited resources for regional Sign languages. This research aims to create a reliable recognition system for GSL, a regional variant used by the deaf and mute population in Gujarat, India. Few people can understand Sign Language, making it difficult to communicate with the hearing impaired. The system describes the potential of hand gesture. By training on the state-of-the-art machine learning about algorithms, it aims to read your hand gesture in real time and convert it into text or sound. The research includes the creation of a comprehensive dataset, preprocessing techniques, and the uses of convolutional neural networks (CNNs) for gesture recognition. Our approach overcomes challenges like gesture similarity, environmental variations, and user diversity, achieving high accuracy. The system not only aims to facilitate communication but also serves as a step toward inclusion, connecting the gap between the deaf and dumb community and the hearing population. The proposed framework has significant implications for education, healthcare, and social integration, flagging the way for future advancements in regional Sign Language Recognition technologies. This study helps to develop an effective human–machine solution for the deaf community.