This was our first time using AI to generate audio dialogues for textbooks and we found both the ultra-realistic and also premium voices excellent to the extent that we were able to fool people into thinking they were real.
There is a wide diversity of accents and languages available, and some of the voices have a range of styles, including emotions and also whispers and shouting, both very helpful.
It's obviously going to be a steep learning curve with so many factors, but the customer support, especially from Joel, was superb. We always got a timely and patient response, and where a glitch had occurred, compensation in the way of extra words to use.
After working with it for a few days, it does become much easier to manage and work with, and we're creating much better results faster now.
With short audio files it can produce very high fidelity results. It produces very realistic and expressive results, and with the most basic plan you can clone up to 15 voices.
Scale your voice generation with PlayAI's Text to Speech models that can clone and generate speech with hyper-realism across any language, accent and dialect.