Next-generation audio models in the API
New speech-to-text and text-to-speech models in the API; developers can instruct how the voice speaks.
For the first time, developers can also instruct the text-to-speech model to speak in a specific way—for example, “talk like a sympathetic customer service agent”—unlocking a new level of customization for voice agents.
Official source
Introducing next-generation audio models in the APIopenai.com · published