Major depression is a common, recurrent, and chronic disease that negatively affects the quality of life and increases the risk of mortality. Several studies have demonstrated that curcumin, the yellow‐pigmented substance of the turmeric, possesses antidepressant properties. The aim of this review is to meta‐analytically assess the antidepressant effect of curcumin in patients with major depressive disorders. We extensively searched the literature until August 2015. The random‐effect model was used to calculate the pooled standardized difference of means (SMD). Subgroup analyses were also performed to examine the effect of different study characteristics on the overall model. Six clinical trials met the inclusion criteria. Overall, curcumin administration showed a significantly higher reduction in depression symptoms [SMD = −0.34; 95% confidence interval (CI) = −0.56, −0.13; p = 0.002]. Subgroup analyses showed that curcumin had the highest effect when given to middle‐aged patients (SMD = −0.36; 95% CI = −0.59; −0.13; p = 0.002), for longer duration of administration (SMD = −0.40; 95% CI = −0.64, −0.16; p = 0.001), and at higher doses (SMD = −0.36; 95% CI = −0.59, −0.13; p = 0.002). The administration of new formulation of curcumin (BCM‐95) had non‐significantly higher effect on depression as compared with the conventional curcumin–piperine formula. We conclude that there is supporting evidence that curcumin administration reduces depressive symptoms in patients with major depression.