Definition
Speech-to-text (STT), or automatic speech recognition (ASR), is technology that converts spoken audio into written text. In video workflows it powers transcripts, auto-captions, filler-word detection and text-based editing.
The transcript is the backbone of modern video editing: captions are timed from it, filler words are found in it, the step-by-step article is written from it, and translations start from it. Fixing a product name once in the transcript fixes every downstream asset.
Explaino turns one screen recording into a narrated how-to video, a step-by-step article and translations.
Free plan · no credit card required