Road accidents remain a major global concern, with countless incidents occurring every hour due to factors such as drunk driving, fatigue, lack of attention, and other distractions. Among these, driver fatigue is one of the leading causes, often resulting in delayed reactions and impaired judgment. Addressing this issue is critical for enhancing road safety. This research introduces a real-time driver drowsiness detection system that utilizes Convolutional Neural Network (CNN) technology to detect early indicators of weariness via eye blink analysis. The system employs a camera to continuously monitor the driver’s face, analyzing blink frequency and eye movement patterns to detect drowsiness accurately. Developed using Python, OpenCV, and Keras, the system operates entirely offline, making it suitable for deployment in vehicles without internet connectivity. When drowsiness is detected, an audible alarm is triggered to alert the driver, helping to prevent potential accidents. Experimental results demonstrate the effectiveness and reliability of the proposed model in real-time scenarios, highlighting its potential as a practical solution for proactive accident prevention. However, the system's reliance on eye blink analysis may be limited by factors such as drivers wearing sunglasses, which can obscure eye detection. This work supports the continuous aspirations to integrate intelligent safety features into modern vehicles, ultimately aiming to reduce road fatalities caused by inattentive driving.