Depression is a leading cause of disability worldwide, yet its detection in low-resource and linguistically diverse settings remains challenging. Conventional self-report measures, such as the PHQ-9, are widely used but may fail to capture culturally nuanced expressions of depressive symptoms, particularly in Nigerian Pidgin-speaking populations. Advances in digital and artificial intelligence technologies offer opportunities to integrate multimodal data, combining self-report responses with vocal biomarkers such as tone, pitch, and speech rate, to improve diagnostic accuracy. The GENSCORE assessment is a novel, culturally adapted, multi-modal tool designed to address these limitations by leveraging text- and audio-based inputs for depression screening. This randomized controlled trial aims to evaluate the diagnostic performance of GENSCORE against the clinical gold standard (SCID-5-CV) and the PHQ-9, and to determine whether the multimodal approach provides incremental value over traditional self-report methods in a Nigerian community setting.