Forum Discussion
In Storyline, can the AI voice dynamically speak the learner's name?
As of now, Storyline's text-to-speech engine can't generate audio files after the eLearning is published. Your use case would be an interesting application for that, however.
As other members have said it's possible - but not easy. I use Microsoft Azure AI Speech Services (really not expensive - you get a good allowance of free text-to-Speech each month). However, to avoid exposing your Authorisation Code to use this service, you need to create a server-side app (I use node.js). This app fields API calls from Javascript code executed in Storyline and in turn calls the Azure AI generative voice service to return audio which it then reads in the voice you have chosen. Not for the feint-hearted, I'm afraid.
I also have it working with Speech-to-text. This time I use a web object which controls the user's microphone and uses JavaScript to send the recorded audio to my server-side app which then returns the transcript and passes it to my Storyline in a text variable.
