The extraction of kratom (M. speciosa) leaf powder was optimized with preliminary extraction to be further optimized with the Box-Behnken experimental design. The individual and interactive effects of process variables (sample-to-solvent ratio, extraction time, solvent concentration) were assessed. The preliminary extraction results showed that ultrasound-assisted extraction (UAE) and methanol were chosen for further optimization. The experimental data were analyzed by Pareto analysis of variance (ANOVA) and second-order polynomial models were developed using multiple regression analysis. The model developed showed a good fit with the experimental data with a high coefficient of correlation (R2) and predictive ability (predicted R2). An optimization study was performed and the optimal extraction conditions were sample-to-solvent ratio value 1.5:10; extraction time of 10 minutes, and methanol concentration of 100%.