The Visual Explorer launched in June of this year in collaboration with the Internet Archive's Television News Archive to make accessible to journalists and scholars their new archive of Belarusian, Russian and Ukrainian television news. We are tremendously excited to announce today the availability of automatic transcripts of all of those broadcasts generated by Google's Speech-to-Text API that will automatically appear in the Visual Explorer when viewing any broadcasts from those channels.
All broadcasts from Russian channels 1TV, NTV and Russia 1 (from March 26) and Russia 24 (from April 25), Ukrainian channel Espreso (from April 25) and Belarusian channel Belarus 24 (from May 16) through the end of October 31, 2022 now have these automatically-generated transcripts.
In all, 24,965 Russian-language broadcasts totaling 67,476,772 seconds (1,124,612 minutes / 18,743 hours) of airtime now have automatic transcripts, along with a total of 8,995 Ukrainian-language broadcasts totaling 16,603,540 seconds (276,725 minutes / 4,612 hours).
View any broadcast from those six channels that aired through the end of October 31st in the Visual Explorer and you will see the new transcript automatically appear alongside the right of the display and clicking on any broadcast will display the transcript of that 30-second clip beneath the video, with subtitling overlay. You can right-click anywhere on the black background of the page in the Chrome browser and choose "Translate into English" to have the transcript automatically translated into English – you only need to do this once per page when it first loads to have the entire transcript (minus the subtitles) translated.
Stay tuned as we roll out automatic transcription for all broadcasts from November 1st onward, which will launch in the next two weeks and automatically transcribe each broadcast within 30 minutes of it airing, allowing near-realtime analysis of the domestic narratives around Russia's invasion of Ukraine.