Using The GPT-4o Audio Preview Model To Generate Voice Playback In Storyline

eLearning Magic Toolkit Version 2.11 introduced support for the GPT-4o Audio Preview model from OpenAI. This new and specialised model is available to select from in the eLM Toolkit settings screen on your platform.

You can see the full range of features in action in our YouTube video covering the release of this new plugin version:

The OpenAI GPT-4 Setting Screen

The GPT-4o Audio Preview model is available to select from the range of current GPT-4 models found in the dropdown list from OpenAI (1).

Once this model has been selected, two new options will appear to choose in the settings beneath (3 and 4). This includes whether you wish to have either text, or text AND audio be returned by the AI system, as well as your choice of voice style from those provided by OpenAI.

Included on the setting screen is a link to an Articulate Storyline 360 project which we have created to showcase how you can utilise this model in your own projects. This includes all custom JavaScript code for the frontend that can be placed behind e.g. a button press in order to begin the voice capture process from the user. You can customise this code as much as required to work for your own project (such as by having the process trigger automatically upon the timeline starting on a slide or layer, as well as generating your own entirely custom code based on our example).

Read the rest of our Knowledge Base pages to make the most of eLearning Magic Toolkit.