Most of us are aware of the fact that voices of different individuals do not sound alike. This important property of speech being speaker dependent is what enables us to recognize a friend over a telephone. The ability of recognizing a person solely from his voice is known as speaker recognition. Applications of speaker recognition are becoming ubiquitous, especially after the increased terrorist activities around the world. Speech patterns can prove extremely useful in criminal investigation and litigation. Moreover speaker recognition can be useful to adapt the machines into their users because a speech interface, in a user's own language is ideal as it is the most natural, flexible, efficient, and economical form of human communication. Speaker recognition can be a useful tool in many other areas such as forensic speech analysis. The choice of features plays an important role in the performance of recognizer. Here we propose prosodic feature set for text dependent speaker recognition. Further we propose the use of Machine Learning (ML) algorithms as classifier to overcome the drawbacks of traditional classifiers.