A model of vocal persona: context, perception, production

We present a contextualized production–perception model of vocal persona developed through deductive thematic analysis of interviews with voice and performance experts. Our findings reveal that vocal persona is a dynamic, context-responsive set of vocal behaviors that frames and bounds expressive interactions—both biological and synthesized—while centering the speaker's agency. By examining how experts adapt their vocal output through both broad persona shifts and fine-grained paralinguistic adjustments, our model identifies a key missing mechanism in current approaches to expressive speech synthesis: the integration of high-level persona prompting with detailed paralinguistic control. This work bridges an important gap in the literature on expressive and interactive speech technologies and offers practical insights for improving voice user interfaces and augmentative and alternative communication systems. Incorporating this vocal persona framework into expressive speech synthesis holds the potential to enhance user agency and embodiment during communication, fostering a heightened sense of authenticity and a more intuitive relationship with voice interaction technology and one's environment.