The company is trying to make the service more accessible to everyone. At a press conference at YouTube's San Bruno, Calif., headquarters, the company touted the feature as useful to not only viewers who are hearing-impaired but also to people who are learning English as a second language.
Video providers are now able to apply for machine transcription on their own videos. And for videos that have not yet been transcribed, a user can request it themselves. YouTube then puts it in a transcription queue, which can take anywhere from an hour to a day--a time Google is trying to make as fast as possible.
The technology that's being used to do the transcriptions works off the same infrastructure as Google's Voice Search, though a company spokesperson said that video presents a distinctly different challenge. Where Google's Voice Search is often taking audio from phones that might have noise cancellation, and only one speaker, videos can have several speakers with multiple dialects. There's also the problem of background noise.
These are challenges Google says it's continuing to work on, alongside support for spoken languages other than English. For now the transcription is limited to English, though Google uses its translation service to then convert those captions into one of the 50 languages it supports.
The option is already live to some users, and should be available to everyone in the next day or so. For more information, be sure to read our live blog.