The previous published data on the association between STK15 F31I and V57I polymorphisms and cancer risk remained controversial. Hence, we performed a meta-analysis to investigate the association between cancer susceptibility and STK15 F31I (42,315 cases and 50,542 controls from 62 studies) and V57I polymorphisms (12,891 cases and 17,391 controls from 18 studies) in different inheritance models. Overall, significant association was observed between F31I and cancer risk when all the eligible studies were pooled into the meta-analysis (recessive model: OR = 1.14, 95 % CI = 1.06-1.24; AA vs. TT: OR = 1.12, 95 % CI = 1.02-1.24; A vs. T: OR = 1.05, 95 % CI = 1.01-1.09). In the further stratified and sensitivity analyses, for STK15 F31I, significantly increased breast cancer (recessive model: OR = 1.16, 95 % CI = 1.02-1.33; AA vs. TT: OR = 1.16, 95 % CI = 1.01-1.33) and ovarian cancer (dominant model: OR = 1.20, 95 % CI = 1.07-1.34; TA vs. TT: OR = 1.19, 95 % CI = 1.06-1.34; A vs. T: OR = 1.15, 95 % CI = 1.05-1.26) risk was found among Caucasians, and significantly decreased lung cancer risk was found among Caucasians (recessive model: OR = 0.65, 95 % CI = 0.49-0.87; AA vs. TT: OR = 0.65, 95 % CI = 0.49-0.88). For V57I polymorphism, significant decreased breast cancer risk was found among Caucasians (recessive model: OR = 0.76, 95 % CI = 0.61-0.95; AA vs. GG: OR = 0.75, 95 % CI = 0.60-0.94; A vs. G: OR = 0.92, 95 % CI = 0.86-0.98). In summary, this meta-analysis suggests that STK15 F31I polymorphism is associated with increased breast cancer and ovarian cancer risk among Caucasians, F31I polymorphism is associated with decreased lung cancer risk among Caucasians, and V57I polymorphism is associated with decreased breast cancer risk among Caucasians.