Zammo contains many voice capabilities. For example, SSML can be used to affect the output of synthetic speech in a predefined Custom Voice. Another capability is called Custom Neural Voice and in this article, we introduce Custom Neural Voice, its capabilities, and more.
Specifically, we cover the following topics:
By the end of this article, you’ll understand what custom neural voice is, why it’s important, how to set it up and when you might want to use it in your conversational AI application.
Custom Neural Voice is a speech feature that lets you create unique synthetic voices in Zammo.
Unlike predefined, out-of-the-box synthetic neural voices, Custom Neural Voice makes it possible for you to create highly natural sounding voices by providing your own audio samples as training data.
Custom Neural Voice is important because, unlike existing out-of-the-box neural voices, custom neural voices sound much more lifelike.
This makes Custom Neural Voices the ideal solution for representing your personal or company brand or to help you create a consistent voice presence.
Some example use cases for Custom Neural Voice in your conversational AI application include, but are not limited to: