There is a critical need for accurate Bangladeshi Sign Language (BdSL) detection systems which create a more inclusive environment for people who are deaf and mute. Recognizing the social isolation faced by deaf-mute individuals due to communication barriers, we propose a system that translates BdSL hand gestures into text, facilitating seamless communication. Our approach leverages the power of YOLOv10, a state-of-the-art object detection model, to achieve accurate and efficient BdSL detection. We train a custom YOLOv10 model on a meticulously curated dataset of labeled BdSL gesture images, focusing on static signs for comprehensive coverage. This in-depth training aims to significantly enhance the robustness and accuracy of BdSL recognition. This technological advancement promises a transformative impact on the lives of deaf-mute individuals. By bridging the communication gap, it fosters greater social inclusion and reduces isolation. Furthermore, this research not only contributes to the field of sign language recognition technology but also holds the potential to bring positive change to the daily lives of those who rely on BdSL. Our proposed method has been tested on a custom dataset of 1949 images of 14 unique signs and obtained an F1-Confidence rate of 86%, Recall-Confidence rate of 98%, Precision-Confidence rate of 100%, and Precision-Recall rate of 90.3% for all classes. The overall average accuracy for 14 unique signs is 90.67%.