[OpenAI · openai.com](<https://openai.com/index/introducing-our-next-generation-audio-models/>)

# Introducing next-generation audio models in the API

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.

1. [New Releases · OpenAI](<https://curation.space/openai/new-releases>)
