This manuscript proposes a hybrid method for drive control using a multilevel inverter (MLI) for electric vehicle (EV) applications. The proposed technique is the joint execution of spiking neural network (SNN), and sand cat swarm optimization (SCSO), hence it is named as SCSO-SNN technique. The primary goal of the proposed technique is to improve the speed tracking performance and, energy efficiency and lessen the torque ripple of the EV. The set of control signals is generated by SCSO and the SNN is used to forecast the optimal control signal of the cascaded multilevel inverter (CMLI). The proposed technique is implemented in the MATLAB software and is evaluated their performance with various present methods. The results show that the proposed method can achieve better performance than current techniques based on speed tracking, energy efficiency, and torque ripple. The proposed method enhanced the total efficiency of the system (96%) and reduced the torque ripple (0.5%) when contrasted with current techniques like Genetic Algorithm (GA), Spotted Hyena Optimizer (SHO), Particle Swarm Optimization (PSO). The proposed method shows a mean of 1.269, a median of 1.212, and a standard deviation of 0.015, indicating high stability and consistency. It also demonstrates lower switching losses (0.159 W) and conduction losses (0.370 W) compared to existing methods, underscoring its superior energy efficiency and effectiveness. [ABSTRACT FROM AUTHOR]