PolyAI Releases Dialog-RSN-1: An Audio-Native Dialog Model That Fuses Turn-Taking, Speech Recognition, Function Calling, and Response

PolyAI launched Dialog-RSN-1, an audio-native enterprise dialog model for real-time voice agents.

The model takes raw audio directly and handles turn-taking, ASR, function calling, and response generation in one pipeline.

PolyAI says the system delivers sub-300ms responses and better containment and latency in customer deployments.

At launch, it is English-only and available only through PolyAI’s platform, not as open weights or a public API.