We studied the timing of the spontaneous vocalization that occurs in dyadic interactions of fathers and their neonates. We recorded 21 fathers speaking to their 2 to 4‐day‐old newborns at the maternity ward and accurately coded all beginnings and endings of paternal and neonatal vocalization, using sound visualization software. Temporal relations between successive and overlapping newborn and father vocalizations were analysed. Results strongly suggest that newborn infants' vocalization timing is related to the timing of fathers' speech and that both newborns and fathers respond to each other within a 1–3 s temporal window, giving rise to sequences of turn‐taking. This study not only shows newborns' awareness of the timing of their partner's expressions but also fathers' readiness to communicate with them right from birth. We discuss the relevance of these findings to the theory of innate intersubjectivity.