In this guided project, you’ll learn how to build your own AI assistant using OpenAI’s pre-trained GPT-3 model. Unlike the popular ChatGPT which communicates with text, your personal assistant will use voice. You will use Watson Speech-to-Text to give your AI assistant the gift of hearing and Watson Text-to-Speech so that your assistant can read the answers back to you.

With a voice-based personal assistant at your beck and call, you’ll be able to get answers, find information, and even have conversations, all without lifting a finger. 

You will build your project using the IBM Skills Network Labs, a virtual lab environment that will provide you with everything you need to complete your project. The only thing you need is a modern web browser like Chrome, Firefox, Edge, or Safari. If you would like to showcase your project or deploy it in production for others to use, we recommend deploying it to the IBM Cloud® Code Engine or a similar fully managed serverless or Kubernetes service. This guided project will teach you how to deploy your assistant to the  Code Engine service.

IBM Cloud® Code Engine is a fully managed, serverless platform. Bring your container images, batch jobs, or source code, and let IBM Cloud Code Engine manage and secure the underlying infrastructure for you. There is no need to size, deploy, or scale container clusters yourself. And no networking skills are required either. You can try it at no charge and receive USD$200 in cloud credits.

At the end of this guided project, you’ll have a fully functional voice assistant that you can deploy anywhere. You’ll also have a solid understanding of how to add voice capabilities to any application using IBM Watson Speech Libraries for Embed, making you well-equipped to tackle more advanced projects in the future.