We are incredibly excited to announce that over the coming 24 hours, all of our Belarusian, Russian, Ukrainian & Iranian television news channels we monitor in collaboration with the Internet Archive's Television News Archive will be upgraded to use Google's new Chirp Universal Speech Model for automated speech transcription from here forward. This immensely powerful new model will result in vastly improved transcriptions, including enhanced transliteration of names and grammatical structure, with especially significant gains for Ukraine's Espreso TV and Iran's IRINN. We are particularly excited by Chirp's multilingual transcription capabilities, which will allow us to explore the degree to which these channels incorporate brief clips in other languages as they excerpt global video.