Mammalian vocal duets and turn-taking exchanges — long, coordinated acoustic signals exchanged between two individuals— are primarily found in family-living, pair-bonded mammals with a socially monogamous lifestyle (some rodents, some lemurs, tarsiers, titi monkeys, a Mentawai langur, gibbons and siamangs). Duetting and turn-taking patterns combine visual, chemical, tactile and auditory cues to produce some of the most exuberant displays in the realm of animal communication. How and why such phenotypes evolved independently across main lineages are fundamental questions at the core of the nature-nurture debate. Duetting styles ranging from antiphonal (non-overlapping) to simultaneous (overlapping) emissions have now been documented in various taxa, some of which are quite reminiscent of turn-taking rules in human conversation. Nonetheless, much remains to be learned about this complex motor skill, and at all four levels of analysis, namely (1) developmental processes, (2) causal mechanisms (3) functional properties and (4) evolutionary history. Given the strong link between this form of coordinated singing and pair-bonding, gaining a deeper understanding of this kind of cooperative behavior will likely shed more light on the deep evolutionary roots of human culture, language and music.