Answers are grounded in this paper and cite their sources.
The increasing integration of generative artificial intelligence (AI) into conversational environments has created new requirements for managing the temporal structure of human–AI interactions. Although existing research has investigated conversational turn-taking, speech-duration control, and time allocation among human participants, the systematic regulation of speaking time independently assigned to human users and generative AI systems remains an insufficiently unified research direction. This paper introduces Generative AI Speaking-Time Regulation (GASTR), a configurable framework that establishes individualized temporal constraints for each participant in a generative AI conversation. The framework supports unidirectional regulation, in which speaking-time limits apply exclusively to either the human user or the generative AI system, and bidirectional regulation, in which both participants receive independently configurable time limits. Unlike conventional conversation-duration limits, GASTR distinguishes individual speaking duration, per-turn allocation, cumulative speaking budgets, and session-level temporal constraints. It further introduces configurable enforcement, countdown mechanisms, pre-limit notifications, automatic interruption, time-extension requests, pause-and-resume operations, and adaptive temporal allocation. The framework is designed to accommodate text-based conversations, spoken interactions, multimodal communication, and multi-agent conversational environments. To the best of our knowledge, this paper presents the first explicitly integrated conceptual framework centered on independently configurable speaking-time regulation for both human and generative AI participants, including unidirectional and bidirectional control within a unified architecture. This contribution is distinguished from existing work on controlling the duration of AI-generated speech, conventional turn-taking, and time allocation in human-only meetings. The paper establishes the conceptual foundations, operational definitions, architectural components, mathematical formulation, implementation principles, evaluation methodology, and ethical considerations necessary for developing speaking-time-regulated generative AI systems.
No takes yet. Share an insight, caveat, or question.
Jincheng Zhang (2026) studied this question.
Synapse has enriched 8 closely related papers on similar clinical questions. Consider them for comparative context: