In the early text-based, green-screen days of computers we talked about building a “GUI” – a Graphical User Interface. Nowadays we need to increasingly consider the “VUI” or Voice User Interface.
But VUI’s are not necessarily new. We have had them for a long term with IVR – Interactive Voice Response or the dreaded voice menus that people constantly yell “operator!” over, or furiously hit 0 until a human picks up.
However, with Siri, Alexa and other bots from the smart speaker ecosystem are changing the perception of voice response. Voice search is as simple as asking your smartphone a question which is transcribed and entered as a text search in Google or Bing.
While voice searching is straight forward on a smartphone where results are displayed for browsing, voice interactions with a program are more complex and nuanced. Not only does the system need to maintain context by chaining together questions and responses, but the user has to remember bot responses and have a way of capturing details beyond their working memory. A pure voice interface is blind – there are no visual cues for the user or the system.
Voice can be paired with a visual interface in products like the Amazon Echo show which has its own design nuances.
In this session we will explore the implications of building voice capabilities whether that is for conversational commerce, voice-based search or chat/voice hybrid interfaces.