 The review synthesizes research on using speech patterns from smartphones to diagnose and monitor mood disorders, showing that voice data alone has reasonable accuracy in predicting mood states and fluctuations based on objectively monitored speech patterns. However, many challenges remain around the robustness, cost-effectiveness, and acceptability of such an approach, and further work is required to build on current research and reduce heterogeneity of methodologies as well as clinical evaluation of the benefits and risks of such approaches. This article was authored by Olivia Flanagan, Amy Chon, Part Her Roup, and others.