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

PolyAI released Dialog-RSN-1, an audio-native dialog model that processes caller audio directly, integrating turn-taking, speech recognition, function calling, and response generation into a single model while keeping text-to-speech separate for controllable output. The company reports sub-300ms response times in live deployments.

PolyAI has introduced Dialog-RSN-1, a dialog model that perceives caller audio directly instead of reading an ASR transcript. It fuses turn-taking, speech recognition, function calling, and response generation into a single audio-native model, keeps TTS separate so the output voice stays controllable, and runs as a request-based LLM rather than an always-on stream. PolyAI reports sub-300ms responses in live deployments. The post PolyAI Releases Dialog-RSN-1: An Audio-Native Dialog Model That Fuses Turn-Taking, Speech Recognition, Function Calling, And Response https://www.marktechpost.com/2026/07/30/polyai-releases-dialog-rsn-1-an-audio-native-dialog-model-that-fuses-turn-taking-speech-recognition-function-calling-and-response/ appeared first on MarkTechPost https://www.marktechpost.com .