In this study, the effect of the user choice on social responses to computer-synthesized speech is investigated. Three previous findings about social responses to computersynthesized speech (i.e., social identification, proximate source orientation, and similarity attraction) were tested using the choice paradigm. Social identification and proximate source orientation effects were found even when users had chosen a computer voice at their discretion. In addition, the primacy effect in the user choice prevailed: Participants were more likely to select whatever voice that they heard first between two options. The similarity attraction effect, however, was negated by the cognitive dissonance effect after user choices. The robustness of social responses, its implications for human-computer interaction, and the importance of the user choice in voice-interface designs are discussed.