Over the past few months, we’ve invested in advancing the intelligence, capabilities, and usefulness of text-based agents—or systems that independently accomplish tasks on behalf of users—with releases like Operator, Deep Research, Computer-Using Agents, and the Responses API with built-in tools. However, in order for agents to be truly useful, people need to be able to have deeper, more intuitive interactions with agents beyond just text—using natural spoken language to communicate effectively.

Today, we’re launching new speech-to-text and text-to-speech audio models in the API—making it possible to build more powerful, customizable, and intelligent voice agents that offer real value. Our latest speech-to-text models set a new state-of-the-art benchmark, outperforming existing solutions in accuracy and reliability—especially in challenging scenarios involving accents, noisy environments, and varying speech speeds. These improvements increase transcription reliability, making the models especially well-suited for use cases like customer call centers, meeting note transcription, and more.

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. This enables a wide range of tailored applications, from more empathetic and dynamic customer service voices to expressive narration for creative storytelling experiences.

We launched our first audio model in 2022⁠ and since then, we’ve committed to improving the intelligence, accuracy, and reliability of these models. With these new audio models, developers can build more accurate and robust speech-to-text systems and expressive, characterful text-to-speech voices—all within the API.