As a part of one of our client’s expansion of services, we introduced a new set of capabilities to our existing Text-to-Speech product, which allowed for more of a dynamic script. Historically, what we have enabled is a user to dial into a number and then listen to a static list of risks associated with a product.
Here’s Looking At A More Dynamic Script
Now, however, we have built a UI in which users can type in crucial information about a loan. Then they’re fed into our system, which dynamically creates a script – that includes the data fed into the system – to convey the terms and conditions to the user.
Traditionally this would take much of the user’s time to put together on their own. Now it’s being digitized so that the scripts are built pertaining to the product. We also save the RM’s time in reading out the terms and conditions, so that the RM can focus on other – more productive tasks – while the user listens to the terms and conditions.
We are still in the implementation phase. However, the concept has been tested. Previous iterations of the product (albeit without the dynamic script generation abilities) have successfully been implemented at the bank and is now widely adopted.
We are continually improving the abilities of Text-to-Speech abilities. One of the current drawbacks of the product is the fact that it sounds too machine-like, i.e., too robotic. The team is currently reviewing ways in which we can make the sound to be more human-like and sound more natural.