Welcome to another episode of The Speechly Podcast and the next episode in the "Designing and Developing Voice UIs" series.
In this series we will be having open discussions with members of the Product Team at Speechly exploring topics related to the Design & Development of Voice UIs in everyday technology. We will discuss existing best practices for the Design & Development of Voice UIs as well as emerging topics relevant to the progression of Voice UI technology.
Today I am joined by Otto, Co-Founder and CEO at Speechly, to have a discussion on Voice Form & Tap-To-Talk Components for React and Web as well as Evaluating Deployed Voice UI Models.
We dug into topics such as:
- Why are “Voice Forms” a good use case for a Multi-Modal Voice Interface?
- What are the benefits of Tap to Talk vs a Wake Word in Mobile and Web based Voice experiences?
- What are the benefits of evaluating the accuracy of a Voice UI Model configuration using a set of test utterances vs just testing with real users out of the gate?
- We also had some great questions around topics like privacy from those listening live.
I hope you enjoy this conversation with Otto on The Speechly Podcast!
Follow Speechly:
Twitter - @SpeechlyAPI
