The audio moderation technology works by recording and automatically transcribing 10-second snippets of audio in livestreams of 10 or more people. The text is then automatically scanned using AI to detect problematic content, such as nudity or drug use. Yubo sends alert pop-ups to tell users that they’re doing something inappropriate while it’s happening.

Yubo says only text that contains words or phrases that violate the app’s policies are flagged for review by Yubo’s. The incidents are then investigated in real time to determine what actions should be taken. Transcripts with no suspected violations are not reviewed and are automatically deleted after 24 hours. Transcripts that are flagged and require investigation internally or by law enforcement are stored for up to a year.

“Our expansion of audio moderation technology is not only a key element of Yubo’s ever-evolving safety product roadmap, but a critical development in expanding the parameters of online safety industry-wide,” said Yubo COO Marc-Antoine Durand in a statement. “There is still a lot of progress to be made in the area of voice detection, but we are proud to be forging a path for our peers by being the first to launch audio moderation with Hive and helping make this tool more reliable and effective through this trial.”

Founded in 2015, Yubo users hang out in livestreaming rooms where they can socialize, play games and make new friends. Unlike other social media platforms, there aren’t creators on the platform broadcasting to fans. Instead, Yubo’s main focus is on helping users socialize naturally.

Yubo expands its real-time audio moderation technology to the U.K., Australia and Canada by Aisha Malik originally published on TechCrunch