[autoencoders]

The edit on the page is not the best. I agree!. Mainly, if your recording is unnatural (like that one) the edit is also unnatural. However, the tool works better in an interview podcast. I would strongly recommend to just upload a sample, and you would see a big difference.

Regarding if ML would be indistinguishable from humanly edit. Hard to tell. I think it will be like self-driving cars in the future. 98% edits good 2% bad edits.

[jffry]

This is a super cool product, congratulations. I especially like the extremely clear value proposition on the homepage. I know what this is and who it is for right away.

My first impression of the unnatural recording was that it must be that way to make it easier to get a good result, but then the result doesn't sound natural either. I think a lot of this is the drawn out uterrances made the speaker vary their pitch/cadence a lot more than usual. Once edited to remove the gap, the sudden change is very noticeable.

I don't think that's due to your software, but just a fact of the unnatural source audio. I think a different, more realistic source audio could let you have a really awesome example, without it being disingenuous or not representative of real-world results.

Thanks for jumping into the ring and answering questions in here!

[autoencoders]

Thank you for the suggestion and your impression. I agree, a better example would highlight it better.