OBJECTIVE: Depression is common in diabetes and linked to adverse health outcomes. This study evaluated the efficacy of a guided web-based intervention in reducing depression in adults with type 1 and type 2 diabetes. RESEARCH DESIGN AND METHODS: A total of 260 participants with diabetes and elevated depressive symptoms (Center for Epidemiologic Studies Depression Scale [CES-D ≥23]) were randomly assigned to the GET.ON Mood Enhancer Diabetes (a guided self-help intervention, n = 130) or a brief online unguided psychoeducation program for depression (n = 130). The primary outcome was depressive symptoms severity (CES-D). The secondary outcomes included diabetes-specific emotional distress (Problem Areas in Diabetes [PAID] scale) and participant satisfaction (adaption CSQ-8). Data were collected at baseline and 2 months after randomization. To identify differences in outcome between the groups, we used analyses of covariance with the baseline CES-D score as covariate on both intent-to-treat (ITT) and per-protocol (PP) basis. RESULTS: Compared with the control group, the intervention group showed significantly less depressive symptom severity at posttreatment based on ITT (d = 0.89) and PP analyses (d = 1.00). The intervention participants displayed a significantly larger reduction in diabetes-specific emotional distress (d = 0.58, ITT). The intervention appeared to be acceptable to the participants; 95% (n = 121) would recommend the training to a friend with diabetes in need of psychological help. CONCLUSIONS: A guided, web-based intervention to reduce depression in adults with type 1 and type 2 diabetes is effective in reducing both depressive symptoms and diabetes-specific emotional distress.