Google has officially introduced an advanced auto-caption feature for all YouTube users.
According to company spokesperson Hiroto Tokusei, YouTube’s auto-captioning leverages certain speech-to-text algorithms found in Google’s Voice Search to automatically generate requested video captions.
“The video owner can also download the auto-generated captions, improve them, and upload the new version,” explained Tokusei.
“Viewers can even choose an option to translate those captions into any one of 50 different languages – all in just a couple of clicks. There will even be a ‘request processing; button for un-captioned videos that any video owner can click on if they want to speed up the availability of auto-captions.”
However, Tokusei noted that the auto-captioning feature is currently only available for videos in which English is spoken.
“[But] we plan to broaden the feature to include more languages in the months to come. [And] just like any speech recognition application, auto-captions require a clearly spoken audio track. Videos with background noise or a muffled voice can’t be auto-captioned.
“Auto-captions aren’t perfect and just like any other transcription, the owner of the video needs to check to make sure they’re accurate. In other cases, the audio file may not be good enough to generate auto-captions. But please be patient – our speech recognition technology gets better every day,” he added.
