AI Voice/text to speech workflow improvements
I love this feature in then new version 12.5 with AI, however the workflow needs to be simplified. In many cases, I want the text I have on the screen to be spoken. I need to copy all that, open the text-to-speech, then paste the same information into the speech caption box, then click generate. Add a right-click option or a button that allows me to pick a text object already on the slide, and just convert it without all the duplicate effort.
David McNally
shared this idea
-
Mark Whitney
commented
I agree with all this and hope we can one day have it generate speech from the text on the screen and then auto-generate closed captions from that audio. I would also need to split the captions so that only one line appears across the screen at a time.
I mean what you guys have done here is incredible and these changes don't seem like all that much in comparison.
-
Also, after I add the text to speech audio, I need to re-adjust all the timelines to match the end of the slide for each object in most cases. When the timeline needs to change to fit the audio, add an option that allows me to adjust all objects to match if I so choose.