Near-infrared (NIR) spectroscopy is an effective tool for analyzing components relevant to tea quality, especially catechins and caffeine. In this study, we predicted catechins and caffeine content in green and black tea, the main consumed tea types worldwide, by using a micro-NIR spectrometer connected to a smartphone. Local models were established separately for green and black tea samples, and these samples were combined to create global models. Different spectral preprocessing methods were combined with linear partial-least squares regression and nonlinear support vector machine regression (SVR) to obtain accurate models. Standard normal variate (SNV)-based SNV-SVR models exhibited accurate predictive performance for both catechins and caffeine. For the prediction of quality components of tea, the global models obtained results comparable to those of the local models. The optimal global models for catechins and caffeine were SNV-SVR and particle swarm optimization (PSO)-simplified SNV-PSO-SVR, which achieved the best predictive performance with correlation coefficients in prediction (Rp) of 0.98 and 0.93, root mean square errors in prediction of 9.83 and 2.71, and residual predictive deviations of 4.44 and 2.60, respectively. Therefore, the proposed low-price, compact, and portable micro-NIR spectrometer connected to smartphones is an effective tool for analyzing tea quality.