Previous studies have shown that infants, including newborns, can match previously unseen and unheard human faces and vocalizations. More recently, it has been reported that infants as young as 4 months of age also can match the faces and vocalizations of other species raising the possibility that such broad multisensory perceptual tuning is present at birth. To test this possibility, we investigated whether newborns can match monkey facial and vocal gestures. Using a paired preference procedure, in Experiment 1 we presented pairs of different visible monkey calls in silence and then in the presence of one or the other corresponding audible call and compared preferences across the silent and in-sound conditions. In Experiment 2, we presented the same monkey visible calls but this time together with a tone analog of the natural calls in the in-sound trials. We found that newborns looked longer at the matching visible call in the in-sound condition than in the silent condition in both experiments. These findings indicate that multisensory perceptual tuning is so broad at birth that it enables newborns to integrate the facial and vocal gestures of other primates and that integration is based on newborns' detection of audio-visual temporal synchrony relations. (Contains 2 figures.)