We introduce three audio models into the API
We introduce three audio models into the API


Author: OpenAI – Duration: 00:04:04
We're introducing three audio models to the API that unlock a new class of voice apps for developers. Using these models, developers can create more natural voice experiences, respond more intelligently, and act in real time: • GPT‑Realtime‑2, our first voice model with GPT‑5 class reasoning that can handle more difficult requests and move the conversation forward naturally. • GPT‑Realtime‑Translate, a new live translation model that translates speech from over 70 input languages to 13 output languages while following the speaker's pace. • GPT‑Realtime‑Whisper, a new streaming text-to-speech that transcribes speech live while the speaker speaks.






