Multi-Modal Systems with the OpenAI API

Create multi-modal systems using OpenAI's text and audio models, including an end-to-end customer support chatbot!

Develop Multi-Modal Applications with the OpenAI API

To build applications that are accessible to as wide an audience as possible, it's important that they can accept inputs in different modalities, like text and speech. In this course, you'll build on your knowledge of OpenAI's text generation models and learn to master their audio models!

Master Audio Applications

Did you know OpenAI developed audio models? In this course, you'll learn to create reliable text transcripts in multiple languages using their speech-to-text models. You'll also flip the script and generate realistic human audio (and in multiple languages!) with their text-to-speech models.

Protect and Moderate AI Applications

AI applications are often designed for a very specific reason, but a malicious actor may try to misuse it in different ways. In this course, you'll utilize OpenAI's moderation models to detect inappropriate user and AI-generated content.

Build Functional Customer Chatbots

You'll complete a case study to create an end-to-end customer service chatbot that will receive customer queries, and use internal resources to respond back to the customer. Not only that, it will respond in their native language and with AI-generated spoken audio!