gpt-realtime

gpt-realtime

A new S2S (speech to speech) model with improved instruction following.
Azure OpenAI
Direct from Azure
Version: 2025-08-28

Direct from Azure models are a select portfolio curated for their market-differentiated capabilities:

  • Secure and managed by Microsoft: Purchase and manage models directly through Azure with a single license, consistent support, and no third-party dependencies, backed by Azure's enterprise-grade infrastructure.
  • Streamlined operations: Benefit from unified billing, governance, and seamless PTU portability across models hosted on Azure - all part of Microsoft Foundry.
  • Future-ready flexibility: Access the latest models as they become available, and easily test, deploy, or switch between them within Microsoft Foundry; reducing integration effort.
  • Cost control and optimization: Scale on demand with pay-as-you-go flexibility or reserve PTUs for predictable performance and savings.

Learn more about Direct from Azure models .

About this model

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 model capabilities

Key Features:

  • Two new voices
  • Improved instruction following
  • Enhanced voice naturalness
  • High audio quality
  • Improved function calling

Quick facts

Model providerAzure OpenAI
TypeAudio generation
LifecycleGenerally available (GA)
Input typeaudio, text, image
Output typeaudio, text
Context window128k
Token limits4096 output