Models · MarkTechPost ·
PolyAI Releases Dialog-RSN-1: An Audio-Native Dialog Model That Fuses Turn-Taking, Speech Recognition, Function Calling, And Response
PolyAI introduced Dialog-RSN-1, an audio-native dialog model that directly processes caller audio and combines turn-taking, speech recognition, function calling, and response generation. It keeps text-to-speech separate and reportedly delivers sub-300ms responses in live deployments.