From the source
- PolyAI's Dialog-RSN-1, a reasoning model built for real-time complex dialog, is now available on AWS Marketplace and
Amazon SageMaker JumpStart, letting AWS customers deploy it as a SageMaker endpoint inside their own AWS environment.
- It is the first PolyAI model offered through AWS Marketplace, and it runs on the same AWS cloud that powers PolyAI's own compute and model training and serving.
- The model perceives a caller's audio directly, reasons about what they need and responds in real time in a single pass, with no separate speech-to-text step and no handoffs between components.
- The endpoint speaks the
OpenAI Realtime protocol, so an existing Realtime client connects through PolyAI's bridge by changing its base URL; audio in is 16-bit PCM mono at 16 or 24 kHz, connections last up to 30 minutes, and the model is English-only today.
- Because inference happens inside the customer's account, deployed in their VPC and accessed through their IAM roles, callers' audio and transcripts stay within a boundary the customer controls, which PolyAI says helps support data residency and auditability requirements.
- Deployment takes one click from the SageMaker AI console Model Hub or a few lines of the SageMaker Python SDK, and PolyAI says the model is already handling live calls in production.






