I started off with 2 codes to make sure I got the audio gram, and voice-cloning features.

After paying a bit around, I then upgraded to full stack.

I see the potential, and I hope that voice-cloning will be available soon, as this is my absolute main reason for purchasing this deal.

When that happens, this deal will be one you regret not getting while you can, as that will be an absolute game-changer.
It will set this app apart from the ton of others out there.

As for the voices currently available - I only checked out the female voices, and a 2-3 of them in English are very life-like and quite impressive!
Since I will also use this app to create hypnotherapy sessions and meditations, then only one of them will work for this specific purpose, and so I'm hoping for more options later - also more of the quiet and ASMR-like.

In the one project I have created so far, the audio gram did not generate. I have now saved the auto-option for audio grams in my profile, so I am expecting it to work next time.

Adding the ability to change colors and the appearance of the waveform, as well as the option to upload a background image, will greatly enhance the experience.
Especially since most of us would want it to blend in seamlessly with our brand(s).

The pro editor for AI voices works pretty well as is, but I would love to have more customization features in regard to pronunciation of specific words.

But... the music generator - it is useless as is.

I've tried many times, but no matter how much or little I write, I always end up with useless noise instead of music or melodies.
I hope more work and AI training will be put into the music generator in the future - but honestly, get the voice-cloing nailed first.

Also, there is (currently) no option to delete the music/results generated, but I assume Sumolings backing this project is what will help to develop the features :-)

I do, however, miss a roadmap - and the ability to add in feature requests (and to upvote those of others).

For instance, I'm hoping for a WordPress plugin for auto-creation of a voice-note that reads the blog post (but not download).

It would also be nice to be able to create a favorite list of all the voices, as to not having to search through them all.

All that said...

I have really high hopes for this app.

Not just for voice-cloning but also the podcast and monetization features and hence went full stack.

I suggest you do the same :-)