OpenAI gpt-realtime
OpenAI gpt-realtime
Version: 2025-08-28
OpenAILast updated September 2025
A new S2S (speech to speech) model with improved instruction following.
Introducing gpt-realtime a new S2S (speech to speech) model with improved instruction. This model merges all speech to speech improvements into a single model to provide a more reliable instruction following. This model excels at instruction following. Key Features:
  • Two new voices
  • Improved instruction following
  • Enhanced voice naturalness
  • High audio quality
  • Improved function calling

Model provider

This model is provided through the Azure OpenAI Service.

Relevant documents

The following documents are applicable:
Model Specifications
Context Length128000
LicenseCustom
Training DataAugust 2025
Last UpdatedSeptember 2025
Input TypeAudio,Text,Image
Output TypeAudio,Text
PublisherOpenAI
Languages27 Languages