Depression is the second most diagnosed disease in the world and is predicted to be the highest by the year 2030. Depressive disorder impacts both on mentally and physically, thus diagnosing this disorder in early stage is essential. Automatic Depression Detection (ADD) system via speech can greatly facilitate early-stage depression diagnosis. Development of such systems demands a standard balanced database. In this work, we present a novel labeled audio distress interview database. To our knowledge, this is the first depression database in Bengali language that contains audio responses from depressed and non-depressed subjects. Alongside this, we present a set of hand-crafted acoustic features that effectively detect depression mood using speech signals. Finally, we justify the quality of our developed database and the efficacy of the feature set in predicting depression using a baseline machine learning (ML) model. We believe that the annotated database will be a valuable resource for use by treating clinicians.Clinical Relevance-This research reports a new speech database in Bengali language for depression detection. This database can be used in healthcare by developing an automatic prediction model for depression detection.