Music appears universally in human infancy with self-evident effects: as many parents know intuitively, infants love to be sung to. The long-term effects of parental singing are unknown, however. In an offset-design exploratory 10-week randomized trial (N = 110 families of young infants, Mage = 3.67 months, 53% female, 73% White), we manipulated the frequency of infant-directed singing via a music enrichment intervention. The results, measured by smartphone-based ecological momentary assessment, show that infant-directed singing causes general post-intervention improvements to infant mood, but not to caregiver mood. The findings also show both the feasibility of longitudinal ecological momentary assessment (retention: 92%; EMA response rate: 74%) of young infants and the potential of longer-term and higher-intensity singing interventions to improve health in infancy.