PersonaKit (PK): A Plug-and-Play Platform for User Testing Diverse Roles in Full-Duplex Dialogue

TL;DR

PersonaKit is an open-source platform enabling rapid prototyping and evaluation of diverse, human-like turn-taking behaviors in spoken dialogue systems, facilitating research on sociolinguistic persona consistency.

Contribution

It introduces a low-latency web platform with JSON-configurable personas and turn-taking strategies for efficient testing of full-duplex dialogue agents.

Findings

Demonstrated the platform's effectiveness with 8 distinct personas.

Enabled comparative A/B studies of turn-taking behaviors.

Facilitated research on sociolinguistic aspects of dialogue systems.

Abstract

As spoken dialogue systems expand beyond traditional assistant roles to encompass diverse personas -- such as authoritative instructors, uncooperative merchants, or distracted workers -- they require distinct, human-like turn-taking behaviors to maintain psychological immersion. However, current full-duplex systems often default to a rigid, overly accommodating ``always-yield'' policy during overlapping speech, which severely undermines character consistency for non-submissive roles. Evaluating alternative, persona-specific turn-taking strategies through empirical user studies is challenging because building real-time full-duplex test environments requires substantial engineering overhead. To address this, we present PersonaKit (PK), an open-source, low-latency web platform for the rapid prototyping and evaluation of conversational agents. Using intuitive JSON configurations, researchers can define personas, specify probabilistic interruption-handling behaviors (e.g., yield, hold, bridge, or override), and automatically deploy comparative A/B surveys. Through an in-the-wild evaluation with 8 distinct personas, we demonstrate that PersonaKit provides an extensible, end-to-end framework for studying complex sociolinguistic behaviors in next-generation spoken agents.