Speech is the strongest mode of discourse through which people express their emotions and ideas through numerous languages. Speech recognition authorization has varied applications as it provides Hassle free procedure which does not require physical contact as in the case of fingerprint authorization. Speech summarisation methods use speech from people as input and produce a condensed form as spoken or written language. Speech synthesis offers a variety of applications spanning from computer technology to medical care, including improving language libraries and reducing therapeutic paperwork load. Every dialect has its unique collection of features for speaking. Despite speaking a comparable language, the speed and dialect differ from individual to individual. This can make comprehending the conveyed message difficult for certain people. Conferences are an important part of every organisation's operation, regardless of if they took place via the web or in reality. Meeting translation and summarization standards, on the contrary hand, are typically disagreeable demands because they necessitate time-consuming workers. This project aims to identify things during meetings like the greatest number of times a person spoke in a meeting to determine his level of inputs and summarisation of insights of meetings for all the employees in the meeting and identifying their insights through the words spoken by them.

Keywords : Speech Recognition, Speech Summarization, Speech Pre-Processing, Spacy, Gensim.