The audio files generated are great, and I like the natural sound of for example German speakers - and out there are only a few tools which can provide such great natural voices.

But frankly speaking, I do miss some really important features like post production editing: once you have generated your audio you will no longer (currently???) have an option to edit anything. And even in pre production you have limited options to enter the text, but how to add pauses? How to change the emphasis? Or - how to change speaker if you for example realize that some parts of your generated audio do not fit?

For example I had a text talking about stocks and exchanges, and the Plugin used some English pronunciation for numbers and some words, although the text has been in German.

I had no chance to change anything afterwards, or to use another speaker. There are some who can pronuciate everything right - but if you need to check every single speaker you have to redo your project instead of just changing the narrator voice.

It would be great if once in the near future there would be options to edit generated projects and change speaker or add some pauses and much more.

Anyway, what is great: ChatGPT Plugin integration. I still need to figure out if I can find the projects I generated in ChatGPT later in the members dashboard, but currently I have not found where I can login into my account.

Well, as I am typing this, you can. Once you logged into both ChatGPT and Speechki you can tell ChatGPT to use a specific ID to create your voice. That is awesome! Anyway, production of audio files (and in this case we are talking about a one minute audio file) can need some time. Obviously, some productions are fast, and some are really really slow.

Overall a promising product with great sounding audio while the app and its features would definitely need some improvements.

Have fun with it and give it a try.