Human detection of AI-generated faces and voices is not domain-general

Recent technological advances have resulted in synthetic faces and voices being perceptually indistinguishable from real faces and voices in typical populations. Faces and voices possess rich personal and social information, meaning synthetic faces and voices, commonly known as "deepfakes" can be used for identity theft, financial fraud, and misinformation campaigns. It is currently unknown whether detection of real versus synthetic content is modality-specific, or whether it generalizes across sensory domains. We conducted a preregistered study in which participants classified real and AI-generated faces and voices. Performance for both face and voice classification was significantly above chance. Using signal detection theory to analyze individuals' ability to classify stimuli, we observed no evidence of a domain-general effect, indicating detection ability may not generalize across face and voice domains and is instead domain-specific. Participants' confidence tracked accuracy for faces but not for voices, suggesting metacognitive insight may be modality-specific. The findings are discussed in terms of whether the absence of an effect reflects classification driven solely by domain-specific abilities or arises from the experimental design itself. Ultimately, in applied contexts, it is important to recognize that expertise in detecting synthetic content might be modality specific.