The Two-Loop Architecture for Voice AI| Voxel51

Building responsive voice AI requires balancing latency with intelligence. This talk introduces a practical architecture that separates real-time conversation from asynchronous reasoning, enabling richer interactions without slowing the user experience. The session covers reusable design patterns drawn from production-inspired conversational AI systems. Abhinav Tushar is an ML engineer and researcher specializing in Conversational AI and Speech Technology. He previously led Machine Learning at Skit.ai, where he built and scaled production voice AI systems from early R&D to enterprise deployment. He is currently co-founder of Panini, an AI product technology lab.