© The Author(s), under exclusive license to APress Media, LLC, part of Springer Nature 2024
S. IfrahGetting Started with Azure OpenAIhttps://doi.org/10.1007/979-8-8688-0599-8_6

6. GPT-4o, DALL-E, and Whisper

Shimon Ifrah1  
(1)
Melbourne, VIC, Australia
 

In this chapter, we will learn how to use the new GPT-4o AI model, how to generate images with DALL-E, convert speech to text with Whisper, and use speech-to-speech chat with GPT4.

GPT-4o

In May 2024, OpenAI released its flagship AI model, GPT-4o. The model is available in Azure OpenAI and provides groundbreaking capabilities.

The model’s name, o, refers to the word Omni, which means multimodal and integrates the following capabilities:

  • Test

  • Vision

  • Audio

It offers a response time of 232 milliseconds for audio ...

Get Getting Started with Azure OpenAI: Deploying and Managing Azure AI and Azure OpenAI Solutions now with the O’Reilly learning platform.

O’Reilly members experience books, live events, courses curated by job role, and more from O’Reilly and nearly 200 top publishers.

Start your free trial