Introducing next-generation audio models in the API

模型更新 OpenAI 原文语言:英文

原文摘录

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.

以下是来源提供的简短摘录,完整内容请查看原文。

参考来源

← 返回每日AI报告