One of the biggest problems that persons with vision impairment face daily is object detection and identification. This paper presents a comprehensive solution by creating an object detection model that can identify objects at a certain distance and relay this information to visually impaired individuals in real-time. The system employs the YOLO algorithm for object detection, which significantly simplifies and speeds up the process. The detected objects are then converted into text, which is subsequently transformed into speech using a text-to-speech conversion method. The implementation involves both software and hardware modifications, including the integration of a Raspberry Pi and a portable camera setup. Our approach achieves an average accuracy rate of 98% in object detection and operates at 4-6 frames per second on a CPU-based system, which is further optimized with GPU usage. Compared to similar systems, our method offers superior real-time performance and accuracy. This technology can be easily integrated into portable devices, providing a cost-effective and reliable tool to help blind individuals navigate their environment safely.