Human face-to-face communication is essentially audiovisual. Typically, people talk to us face-to-face, providing concurrent auditory and visual input. Understanding someone is easier when there is visual input, because visual cues like mouth and tongue movements provide complementary information about speech content. Here, we hypothesized that, even in the absence of visual input, the brain optimizes both auditory-only speech and speaker recognition by harvesting speaker-specific predictions and constraints from distinct visual face-processing areas. To test this hypothesis, we performed behavioral and neuroimaging experiments in two groups: subjects with a face recognition deficit (prosopagnosia) and matched controls. The results show that observing a specific person talking for 2 min improves subsequent auditory-only speech and speaker recognition for this person. In both prosopagnosics and controls, behavioral improvement in auditory-only speech recognition was based on an area typically involved in face-movement processing. Improvement in speaker recognition was only present in controls and was based on an area involved in face-identity processing. These findings challenge current unisensory models of speech processing, because they show that, in auditory-only speech, the brain exploits previously encoded audiovisual correlations to optimize communication. We suggest that this optimization is based on speaker-specific audiovisual internal models, which are used to simulate a talking face.