It's funny, over the course of time of using Descript, I've WASTED credits and recording edit time repeating processes over and over trying to get different results with my audio cleanliness. Sometimes the filtering would wipe out entire yells, laughs, drawn out vowels or my natural "drawl" and I'm finding it seems to be doing less of the damage now a days. Typically I have to save a .wav of an unfiltered version of my project and then a Studio Sound filtered version then bring it to a different app entirely so I can cut and blend the parts Descript did well and did horribly. Usually it's things regarding inflection and volume. If I want to keep a giggle, yell, voice change in the audio for comedic effect, Descript typically erases them or changes the way they sound entirely. So I either have to rerecord them outside the app or sub it out for the original unfiltered take. It would be AWESOME if I could do everything exclusively on Descript, especially since I'm paying for it. So, is an adaptive AI Speaker based on one created with my voice, that can learn my "quirks" and complexities of my individual voice over time something that is in the cards down the line?

I would like to request that the ai voice recorder would allow longer scripts with the initial disclaimer added. The additional scripts would allow better training and better sounding ai voice algorithms. The scripts now make the voices sound robotic and no flair or feeling added. I know I cannot be the only one with this issue.