Image for post
Image for post

When I was nine years old, I had a friend over and we played for hours in my basement recording our own radio show on a cassette recorder and playing back the recording. We’d delight in the freedom to be completely uncensored and use all the profanities we could think of at the time. There was something exciting about hearing out loud your thoughts through a speaker.

Fast forward to five years ago when we first gave out the Ubis to early backers of our Kickstarter. It shipped with the ability to do something similar to what people can do with Alexa blueprints right now — customize the response. Within minutes of the first devices coming online users were programming profane responses.

At first, it was funny to see that people were gravitating so quickly to this interaction. Then, we read closer the terms and conditions of the different text to speech providers and realized that you weren’t supposed to send swear words through their service.

We ended up playing a cat and mouse game of filtering new swear words as we discovered them. However, this was necessary to prevent a violation. Five years later, we see that this issue is still prevelant, even with our Ubi Portal Prototyping Skill for Alexa.

The lesson… in building Skills or Actions that engage content outside of your creation, add a profanity filter or risk delisting!

Written by

Independent daily thoughts on all things future, voice technologies and AI. More at

Get the Medium app

A button that says 'Download on the App Store', and if clicked it will lead you to the iOS App store
A button that says 'Get it on, Google Play', and if clicked it will lead you to the Google Play store