Talking faces constitute a major part of an infant’s perceptual experience. Through the process of watching and listening while people speak to them, infants have the opportunity to acquire cognitive, linguistic, social, and emotional skills. The acquisition of these higher-level skills depends, in part, on infants’ ability to perceive and integrate the audible and visible attributes of speech. The present paper describes the findings from a series of studies examining infants’ perception of audiovisual speech. The focus of these studies was to determine how the audible and visible attributes of speech contribute to infants’ perception of audiovisual speech across the first year of life. The findings show that responsiveness to various features of faces and voices changes throughout early human development and that intersensory integration of these features depends on the nature of the information, its source modality, and the infant’s developmental age.