Azure OpenAI Service unveils GPT-4o-Realtime-Preview with audio and speech

Written By Nolaine Puig

The public preview of GPT-4o-Realtime-Preview for audio and speech marks a significant advancement in the Microsoft Azure OpenAI Service, enhancing its capabilities with cutting-edge voice technology. By integrating advanced voice capabilities into GPT-4o, this update significantly broadens its multimodal functionalities, highlighting Azure's continued leadership in AI, especially in speech technology.

GPT-4o-Realtime-Preview powerful voice capabilities and multimodal features:

  • GPT-4o-Realtime API: Go beyond text-driven AI with natural voice interactions for innovative voice-driven apps.

  • Azure AI Studio early access: Test GPT-4o-Realtime’s audio features in a playground before production.

  • Faster responses: Get near-instant voice replies that outshine typical text-to-speech engines.

  • Natural conversations: GPT-4o provides human-like conversations for an authentic experience.

  • Multilingual support: Enjoy a wide range of supported languages that can be applied to global-facing applications.

Nolaine Puig
Previous

Microsoft launches Azure ND H200 v5 series cloud-based AI supercomputing clusters
Next

Microsoft fine tunes customization and support for new models in Azure AI