Abstract In this paper four different Soft Computing (SC) models have been proposed which are able to predict AC breakdown voltage of the two solid insulating materials, namely Leatherite Paper and Manila Paper. The predicted voltage is a function of four input parameters, such as, the thickness of the insulating sample t, void depth t1, void diameter d and relative permittivity of the materials εr. The requisite data on the breakdown voltages are obtained after statistical analysis of the experimental observations performed with a cylinder-plane electrode system by step-stress method. The voids are artificially created for initiation of Partial Discharge (PD) with different depths and diameters. The proposed SC models seem to be capable of predicting the breakdown voltages quiet efficiently and within a small value of mean absolute error. In order to get a better insight of the breakdown phenomenon, the two solid insulating materials have been observed using a Scanning Electron Microscope (SEM). The SEM images clearly show the degradation taking place in these materials leading ultimately to the breakdown.