One of the biggest challenges with voice assistants is that they sound like humans… almost. The almost problem is more profound than it may at first seem, though. Because the voices are almost human, we as users tend to graft human expectations onto these interfaces that simply aren’t yet up to the task of conversing intuitively, understanding emotions or building true empathy. As architects of these experiences, we must find ways to set appropriate user expectations and bridge the gap with thoughtful design. The following are three best practices to do so:
Mind the Gaps:
In voice experiences, users insert their emotions most into the negative spaces of conversations.
For example, if a consumer used a customer service skill that had long pauses after each question, the user will channel “are they even listening?!” into that gap. Understanding that these moments will spark the most emotion means that we must anticipate and respond accordingly.
Anticipate:
We don’t always say exactly what we mean.
As designers, we must anticipate and predict intent wherever possible.
For example, if a user checks their balance with a banking app, they might just want to know if they can purchase something instead of the actual available funds. If a user asks Alexa about the weather, they might want to know whether they should bring an umbrella or not, as opposed the the actual temperature etc. The more we can enable the tech to intuit intent and anticipate requests, the more frictionless and empathetic our experiences will become.
Listen:
We think of voice as a “focus group of one” because of the specific nature of conversation.
Users will tell you specifically what they want in voice.
This is a powerful truth that can help voice experiences drive personalization for users and glean qualitatively rich insights for brands.
Portions of this content originally appeared as part of SoundHound’s Finding Your Brand Voice: 6 Ways to Build a Better VUI Guide