kapynInfrastructure

Building ultra-low-latency voice AI applications on AWS

Cartesia shows how to build ultra‑low‑latency voice AI on AWS using State Space Models. The Sonic model delivers sub‑100 ms text‑to‑speech and speech‑to‑text at global scale, and can be deployed on Amazon SageMaker or self‑managed EC2 GPU instances. This demonstrates practical, high‑performance voice solutions for developers.

AWS ML Blog·Nov 3, 2026

Opening Kapyn…