In last many years, work has been done in audio processing. However it was not much used in the fields of Electronics and Computers due to its variety of speech signals and complexity. But now with the help of modern algorithms, it is possible to easily recognize the text from the given speech. In this project, we will develop an application, which will tkae the speech as input and give the text which will be specifically related to chemical names. It can also be further extended to provide a baase for various applications like when the text is recognized it can give all the related information of that chemical. We know that there are applications already developed for audio processing and extracting text but they do not work that accurately with chemicals. Hence we make this appliction specially for chemical entities. Here, we use the technique based on Hidden Marcov Model (HMM).