Link to home
Start Free TrialLog in
Avatar of philsimmons
philsimmonsFlag for United States of America

asked on

transcribe

I am running Dragon Naturally Speaking Home Version 13 on my Windows 10 computer.  I got the program so that I can take recorded lectures and convert them to text from a WAV or MP3 file.   I can't find out how to do that.  Please help.  Thanks,

Phil
Avatar of Sam Simon Nasser
Sam Simon Nasser
Flag of Palestine, State of image

check this video
https://www.youtube.com/watch?v=DhJycgvSAPw

go to tools - dragon pad, and while the dragon pad is open, return to the software (video) and click on tools - transcribe recording
ASKER CERTIFIED SOLUTION
Avatar of Joe Winograd
Joe Winograd
Flag of United States of America image

Link to home
membership
This solution is only available to members.
To access this solution, you must be a member of Experts Exchange.
Start Free Trial
Avatar of philsimmons

ASKER

Thanks, Joe.
You're welcome, Phil — sorry to be the bearer of bad news. :(
Well, the $60 version seemed too good to be true.  I got the Professional version, which is still a pretty good deal if it works the way it should :).
Hi Phil,
the $60 version seemed too good to be true
Yeah, you know the cliché. :)
if it works the way it should
Dragon is excellent in its space of voice input/recognition. It has been around for a very long time (I worked for Artificial Intelligence Corporation in 1983 when we had partnering discussions with the Bakers, a husband and wife team who founded Dragon Systems back then). Many folks consider the latest Dragon to be the current gold standard of voice recognition. All of that said, it is not perfect. In terms of your "works the way it should" comment, you need to have proper expectations, or you will be severely disappointed. Voice recognition when the input is coming from a "trained" voice into a high-quality, well-positioned microphone is tough enough; doing it when the input is coming from a recording of a lecture is significantly more difficult. In fact, I have seen instances where it takes longer to do the automated voice recognition followed by the manual correction/clean-up than it does to simply type it in (so-called "heads-down" data entry), especially with supporting transcription tools, such as a foot pedal. I'm in no way saying this to disparage Dragon — I'm just trying to set realistic expectations. Regards, Joe