Depression is a common mental disorder that affects more than 264 million people worldwide. Between 76% and 85% of people in low and middle-income countries receive no treatment for their disorder. There are many barriers to effective treatment such as social stigma, lack of resources, shortage of trained professionals to mention but a few. The purpose of this study was to investigate how machine learning algorithms can be used to create self-help applications that detect depression from vocal acoustic features and suggest remedies so as to bridge the treatment gap.