Skip to Content

Automatic Speech recognition (ASR) for Wistia videos

EdPlus will provide computer generated captions also known as Automatic Speech recognition (ASR) for any video that resides and is served from the Wistia video media player.

These captions are estimated to be about %80-%90 accurate based on the sound quality and the speakers pronunciation of the words. With the goal of %100 accuracy it is a requirement to have the video talent or a subject matter expert perform a quality check and make any needed adjustments. Instructions for submitting Wistia videos for ASR.

Fill out my online form.