OpenAI ↗ · 2025-03-20 19:00 · UTC+8
Introducing next-generation audio models in the API
Model updates OpenAI Source language: English
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.
Short excerpt from the source — open the original for the full text.