In this study, air temperature, relative humidity, and vapor pressure data collected from Manjil station between 1993-2004, were used for wind speed predictions in a future time domain using artificial neural networks. The following combinations of data are considered for this study: (i) month of the year; monthly mean daily air temperature, and relative humidity as inputs, and monthly mean daily wind speed Os output; (ii) month of the year monthly mean daily air temperature, relative humidity, and vapor pressure as inputs, and monthly mean daily wind speed as output. The generalized regression neural networks, multilayer perceptron, and radial basis function neural networks were used in this study. The measured data between 1993 and 2003 is applied for training and the data for 2004 is used for testing. The data for testing were not applied for training the neural networks. Obtained results show that neural networks are well capable of estimating wind speed from sun plc meteorological data. These results indicate that using vapor pressure along with the month of the year, monthly mean daily air temperature, and relative humidity based on a multilayer perceptron network has better performance than the other cases with the mean absolute percentage error of 7.03% (2004).