First of all, let's clarify that there are three ways of adding audio to a book:
Text to Speech (TTS): This is a relatively artificial audio that you hear in some books or even in our training videos. KNiTO is TTS ready and this feature can be activated upon request by publishers.
Readaloud or Media Overlay: This is a real person's narration which is fully synchronized with the text even word by word. It requires voice processing in order to establish the synchrony. ePUB3 supports this feature and KNiTO can provide it once you narration is fully processed and made ready.
Interactive Audio: This is what we will answer. You can record audio of a page or chapter or a line of text and embed it into your file. Please see a short video here or watch it in below: