Audio Models in the API

Olivier Godement, Jeff Harris, Iaroslav Tverdokhlib, and Yi Shen introduce and demo three new audio models in the API—two speech-to-text models and one text-to-speech model—and an audio integration with the Agents SDK, making it possible to build more intelligent and customizable voice agents.

Dive into the demo at openai.fm and learn more in our blog: https://openai.com/index/introducing-our-next-generation-audio-models/