In this paper, the nonlinear autoregressive model with exogenous inputs (NARX) is proposed for wind speed forecast. Forecasting wind speed is a challenging task in wind energy research domain which influences the dynamic control of wind turbine and for system scheduling. The aim of this study is to obtain suitable forecast model for wind speed with time series input variables such as wind direction, humidity, pressure and time. The meteorological data observed with 15 minute time intervals is used for the model and the performance is evaluated and compared with the back propagation neural network (BPNN). The result shows that the proposed model outperforms the BPNN based on the metrics used.