OpenAI launches three new real-time voice models for reasoning, translation, and transcription, included in its Realtime API (Zac Hall/9to5Mac)

Techmeme ·

OpenAI released three specialized real-time voice models for its Realtime API covering reasoning, translation, and transcription capabilities, expanding its audio API offerings beyond the base model.

Categories: Model Releases

Excerpt

<a href="https://9to5mac.com/2026/05/07/openai-has-new-voice-models-that-reason-translate-and-transcribe-as-you-speak/"><img align="RIGHT" border="0" hspace="4" src="http://www.techmeme.com/260507/i33.jpg" vspace="4" /></a> <p><a href="https://www.techmeme.com/260507/p33#a260507p33" title="Techmeme permalink"><img height="12" src="http://www.techmeme.com/img/pml.png" style="border: none; padding: 0; margin: 0;" width="11" /></a> Zac Hall / <a href="https://9to5mac.com/">9to5Mac</a>:<br /> <span style="font-size: 1.3em;"><b><a href="https://9to5mac.com/2026/05/07/openai-has-new-voice-models-that-reason-translate-and-transcribe-as-you-speak/">OpenAI launches three new real-time voice models for reasoning, translation, and transcription, included in its Realtime API</a></b></span>&nbsp; &mdash;&nbsp; OpenAI has just released three new realtime voice models that it says will &ldquo;unlock a new class of voice apps for developers.&rdquo;&nbsp; Each new voice intelligence model &hellip; </p>