From the course: Azure AI for Developers: OpenAI Services and Generative AI Models

Unlock this course with a free trial

Join today to access over 24,900 courses taught by industry experts.

Audio chat with a chat model

Audio chat with a chat model

- [Instructor] And last but not least, we have the real-time audio models. These powerful models combine the power of chat models with text-to-speech and speech-to-text. They're so blazing fast in transcribing and generating audio that it could feel like you're talking to a human. So let's go back to the Azure AI foundry and see how we can make use of them. In the AI Foundry, we go back to our model catalog, we click on Inference Tasks and choose for the option Audio Generation. And there we need to make use of the real-time models. So we click on it, we click on Deploy, and we go through the steps like model version and as well the location where you want to send the data to. Now I've already created one, we go back to our deployments and we have it here. We have our endpoint and we have our key. Now, instead of going into codes, I want to share with you an repository on GitHub, because this audio real-time is very complex. Now, if you look at the schematic of this repository of how…

Contents