Theoretical accounts suggest an increased and automatic neural processing of emotional, especially threat-related, facial expressions and emotional prosody. In line with this assumption, several functional imaging studies showed activation to threat-related faces and voices in subcortical and cortical brain areas during attentional distraction or unconscious stimulus processing. Furthermore, electrophysiological studies provided evidence for automatic early brain responses to emotional facial expressions and emotional prosody. However, there is increasing evidence that available cognitive resources modulate brain responses to emotional signals from faces and voices, even though conflicting findings may occur depending on contextual factors, specific emotions, sensory modality, and neuroscientific methods used. The current review summarizes these findings and suggests that further studies should combine information from different sensory modalities and neuroscientific methods such as functional neuroimaging and electrophysiology. Furthermore, it is concluded that the variable saliency and relevance of emotional social signals on the one hand and available cognitive resources on the other hand interact in a dynamic manner, making absolute boundaries of the automatic processing of emotional information from faces and voices unlikely.