Overall I'm pleased with the product. It has already served me well with one client and the client loved the results.

The fact that I was able to type out a script and have an "AI" software immediately turn text into a speech (voice-over) that needed minor adjustments is amazing in itself. The software has a lot of voices to select from, but the neural voices is where it's at. They sound the most realistic. So real that when I showed a presentation to a couple friends, they had no idea that it was speech to text technology. A big bonus to using the software is that they also have a decent library of music that you can add in the background. Getting VoiceOver software and music all in one package was a no-brainer decision for me. I will be using this program for a variety of presentations, ads, or internal uses. Using the program is pretty straight forward. If you need help, they provide a link with video tutorials to help you out and they are very easy to follow.

It's not a big deal, but when you make changes to your text with gaps, phonetic grammar text to help sound a word out like you want, it doesn't refresh on it's own in the text field when you hit play. You have to refresh by clicking "generate TTS" button. But.... it does make sense, too. It needs a refresh to know you changed something and the program needs to know in order to make the change. (it doesn't take but a few seconds to refresh)

As a new user I can see a lot of potential. I really like the TTS Neural Voices, keep develop team happy!!

I'd really like the TTS Neural Voices, cheers to de Dev Team! Great customer support! Wish list: * Direct implementation within Pro Tools, like Soundly App. * WAV format. At least 44.1khz/16 bits. * Please more TTS Neural voices in Latin Amerian Spanish region (LATAM): MX, AR, CO, BR. * SSML script files Import function. * Function please add mood states: . Lot of work I know, but maybe just the basics? That would speed up and save a lot of time to my post team with pitch n time contour in the chain to achieve deeper layers of interpretation needed in advanced implementations. * Personal Voice Profiling (only owner usage), with machine learning follow up to get specific types of narrators. That's something we would pay for right now. Develop our own personal TTS Neural Voice Library and the capability of keep training them. Maybe a partnership with other brand? Or allowing usage of our external generated TTS Neural Voice profiles? This would be a real level up.

* An offline app extension for script and editing. * The main thing I dislike is that if I want to edit the exact same input text you have to spend credits. I'm not talking of changing/adding words, that's clear as water. I refer to the obvious need of editing script after hearing the rendered interpretation, NOT changing a single word. For example pauses in specific spots, punctuation to get clouser and not an upper. Modify the speed and tone of a phrase or word, not the hole. I get the implications in the monetization and real usage control. But that could be fixed with a really low quality preview for the "editing stage" after listening the first render. When the file is downloaded or saved . For big productions this has a big impact in the monthly limit, credit usage, obviously. And mainly cost estimations, since you don't know how many passes you will need to get a name in other language to sound right modifyng fonetics, etc.

Not bad.

The ease of creating voices with just pasting my script.

Most of the voices provided are not natural.

I use it daily and I recommend it to others to use it

user-friendly and high quality compared to the low price

Nothing to mention, my experience using voicely is very pleasant

I like the software, easy to use

Easy to use, you can open and add text and it convert easy to voice

Languages not support all available languages like tamazight