An Automatic Sign Language Recognition System is a technology designed to reduce the communication barrier between individuals who rely on sign language and those who do not. The system employs computer vision and machine learning techniques to interpret and translate sign language gestures into text or speech, enabling seamless communication between people with different abilities. In our research, the system achieved a high accuracy rate of 90% for the classes ‘A’, ‘G’, ‘E’, ‘B’, and ‘C’, demonstrating its proficiency in recognizing these gestures. For the classes ‘D’, ‘F’, ‘H’, ‘M’, ‘L’, ‘J’, ‘0’, ‘P’, ‘X’, and ‘Z’, the system maintained an accuracy rate between 80 and 90%, showing reasonable effectiveness. However, certain classes fell within an accuracy range of 80–85%, indicating specific areas where further optimization is needed. The system achieved F1 scores of approximately 0.946, 0.916, and 0.896 for classes with 90%, 85%, and 82% accuracy, respectively, highlighting its balanced performance across different gesture categories. Designed to be user-friendly and accessible, the system offers real-time translation capabilities across various devices and platforms, such as smartphones and wearables. This sign language recognition system contributes to Human–Computer Interaction (HCI) by providing a practical and inclusive solution, ultimately aiming to enhance accessibility and inclusivity, bridging the communication gap between hearing and hard-of-hearing individuals.