Condition monitoring and predictive maintenance play a key role in the maintenance of an electrical machine. In this study, to monitor the condition of the induction machine, torque is predicted from the acquired acoustic signals. The acoustic signals collected from different locations of an induction motor are analysed using dyadic wavelet transform for various load conditions. The predicted torque is computed using multiple regression method by extracting the root mean square and mean statistical features of the processed acoustic signal. The percentage error is approximately 5-10% at different location validating the feasibility of using acoustic signals for condition monitoring of machines. In addition, the harmonics induced in the healthy machine due to various acoustic sources is verified using acoustic spectrum. Also, using Pseudo spectrum MUltiple SIgnal Classification algorithm, the pattern and peak decibel for the acquired acoustic signal at different locations are analysed. For any number of samples, the patterns are unique for each location at different speeds. The results obtained validate that pattern analysis method can also be used for condition monitoring and predictive maintenance in electric machines. © 2017, The Institution of Engineering and Technology.