Virtual Voice Out Of Beta

BobbyBrandt

Virgin Wannabe
Joined
Apr 7, 2014
Posts
3,040
I received an e-mail today from Kindle Direct Publishing which indicates that the "Virtual Voice" program that Amazon had been beta testing is now live.

For background, Amazon has had an online application for several years in their web services portfolio that converted text to speech using AI-generated voices, called Amazon Polly. It is one of the most robust TTS applications I have seen, but still required significant modification of the text and punctuation to see output that resembled human speech. It also came at a price, but it wasn't too bad.

About a year ago, Amazon launched a beta of their Virtual Voice program that allowed the selected authors the option of using a derivative of the Amazon Polly platform to create audiobooks directly from any e-books already published on their site. The converted audiobooks would then be available for sale on both Amazon and their Audible sites.

The "studio" platform that allows you to edit the content to insert pauses, select voices, and otherwise manage the audiobook creation is limited, and you can only have a single voice per chapter/part. You cannot add additional effects or music, and the only way to get a download of your audio is for you to buy it yourself. The purchased *.aax files can then be converted to MP3 or other formats with a variety of third-party apps.

The limits of the program, including some adult content disclaimers that will get automatically added to most erotic stories, will make it unsuitable for many.
 
For now. Wait a year.
The adult content issue is actually less of a concern I think than the ability to verbalize sexual acts more realistically using the current TTS capabilities. You can be descriptive, but not as expressive as you can with a human voice actor.
 
The adult content issue is actually less of a concern I think than the ability to verbalize sexual acts more realistically using the current TTS capabilities. You can be descriptive, but not as expressive as you can with a human voice actor.
Agreed.
 
Back
Top