A portable device that acts as a Reading assistant for people using technologies like Natural Language Processing NLP, Speech recognition, and Optical Character Recognition OCR, which takes voice commands as input and gives audio output instantly, recognizing and converting the text in the given source into machine readable electronic version of the text. Artificial intelligence-driven speech recognition processing to make software accessible using human input language. We use this technology to make users interact with computers or devices. Our device can access multiple languages and give instant output. This efficient product runs effectively. The camera used in the device is capable of autofocusing and capturing the image of whatever is placed in front of it and digital documents also. We access the camera by using voice commands which are recognized by the microphone and the program which has been executed in the Edge computing device. Further, we get audio output via headset or speaker. A general-purpose input/output (GPIO) pin is used where the user can simply switch on the device, and then