Urgent.News

What's breaking now, across thousands of outlets.

More in AI

Building ultra-low-latency voice AI applications on AWS

Learn how Cartesia, an AWS Partner, uses purpose-built State Space Models and AWS infrastructure to deliver sub-100ms text-to-speech and speech-to-text at global scale, and how to deploy its Sonic…

  • State Space Models (SSMs) enable sub-100ms voice AI processing
  • Sonic text-to-speech model generates audio with ~90ms latency
  • Ink speech-to-text model offers streaming transcription with multi-speaker handling

More from Tuesday 3 November →