Customers want their own individual voices. It would be great if we could upload audio and text content to generate a custom TTS model for use by the customer's service instance. This way we let the customer do the work involved in building the data needed for the model, and it will sound exactly how they want it to sound.
Why is it useful?
|Who would benefit from this IDEA?||As a company, I want Watson to sound like the person in my comercials|
How should it work?