This project's purpose is to develop a summarization system using Natural Language Processing (NLP) techniques which will assist information retrieval and management from audio. In real-time or near real-time, the system will convert spoken audio into written text and will allow to condense the text to a shorter version while retaining the key information, allowing users to easily access the important information and get a quick overview of lengthy audios. It will use natural language processing and machine learning techniques to analyze the content of a meeting, identify important topics, extract relevant information, and generate a concise summary. This project has many potential applications, including automated closed captioning, meeting and interview transcription, and creating searchable archives of spoken content.