§ feed · storyline
Introducing next-generation audio models in the API
OpenAI releases updated text-to-speech API models that let developers instruct tone and speaking style via natural language prompts.
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.
§ sources1 publication · timeline below