At work we have 16 hours of videos to watch. After e watch these training videos we have to practice it. We have also noticed it is way more effective if someone had a transcript of everything said in the video.
Here is the problem, for the years the only way of doing this was to have some one shot down and watch the video for a few seconds, pause it, write what they said, hit play, pause, etc. This tends to take about an hour for every 10-15 min of video.

So here is the question:
Is there any kind of program or website where it will take the audio do some kinf of talk to text, thus transcribing word for word his videos?