Millions of people around the world face challenges in communication due to hearing and speech impairments, emphasizing the urgent need for alternative methods like sign language. For deaf communities, sign languages are essential for communication, but their variety and lack of universal understanding often create challenges. Traditional methods for recognizing sign language are often difficult to use, which has driven the development of vision-based systems as a more practical and accessible solution. However, achieving real-time performance and adaptability in varied conditions remains a persistent challenge. We present a system that employs YOLO11 for real-time hand gesture recognition, specifically designed to detect hand gestures showing alphabets from A to Z. The proposed model focuses on accurate and efficient detection of hand gestures from images, enabling precise translation into corresponding alphabets. YOLO11 achieves a mean Average Precision (mAP@50–90) of 89.00%, Precision of 96.16%, Recall of 94.10%, and an average inference time of 6.1 ms, outperforming YOLOv10, EfficientDet-D3 and CNN-RNN models. The results demonstrate the effectiveness of our computer vision-based method, which makes use of YOLO11’s fast detection capabilities, in achieving real-time performance and makes it possible for the hearing-impaired community to communicate in an inclusive and accessible manner.