video-to-text

Video to text refers to a software tool that can turn spoken words within a video file into a written words in a text document. 

Used when creating transcripts, it works like this: The "vid-to-text" tool pulls the audio track from your video file, then artificial intelligence or speech-to-text programs use speech recognition to listen to the audio, and then it writes up an output of what was said. 

BTW: You use "video to text" (with no hyphens) as a noun phrase or title, for example: Learn how video to text dictation works. You use "video-to-text" (with hyphens) as an adjective when the phrase describes the noun coming right after it, for example: Video-to-text software makes transcribing fast.

Video-to-text software can turn recordings into meeting notes, including timestamps and who was speaking, it can turn webinars into study guides, and it's the technology behind subtitles and closed captions on YouTube videos. It also helps people who prefer reading or need text references to follow along... all in all, useful technology!