Introducing next-generation audio models in the API
OpenAI released next-generation TTS models in the API with style control, allowing developers to instruct the model to speak in specific personas.
Excerpt
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.
Read at source: https://openai.com/index/introducing-our-next-generation-audio-models