In today’s world, an overwhelming amount of written content is available, making it impractical to convert everything into Braille due to the high costs and large volume. This limits access to vast amounts of scholarly material for the visually impaired. To address these challenges, this project introduces a compact, smart device that allows visually impaired users to access printed text effectively and efficiently. The device uses a camera-based assistive methodology and is implemented on a Raspberry Pi platform, making it a cost-effective and portable solution. The system combines Optical Character Recognition (OCR) and Text-to-Speech (TTS) technologies. The OCR module captures images of printed text through a camera, converting them into machine-readable text, which is then summarized in both English and Hindi using a generative AI model (Gemini). The summarized text is further converted to speech using Google Text-to-Speech (gTTS), enabling users to listen to the key points of the text in both languages. This system enhances accessibility and comprehension by providing a flexible, multilingual solution for the visually impaired, allowing them to access printed materials through real time audio playback. This type of system can be very useful for blind persons in their day to day life and can enjoy their life.