In this paper, a genetic based self-tuning speed controller is proposed for the high-performance drives of induction motors. For a high-performance drives, nonlinear system identification of a motor drive system is required and the results of system identification could provide the controller with information regarding the load variation and parameter variation of the motor. The proposed controller can change the gains of the controller according to system conditions. The gain is composed with system parameter of drive system. For the estimation of system parameters, a genetic algorithm is used. A self-tuning controller is designed that is adequate for the speed control of the induction motor. The availability of the proposed controller is verified through MATLAB/Simulink simulations and is compared with the conventional PI controller.