Nuance Naturally Speaking v. 12.0 – $187.71 with headphones
I’ve never been much of a fan of speech recognition software. Up till very recently, it was crude in the extreme… “You. Had. To. Separate. Your. Words. Like. This.” Although, I have to admit, it could be pretty much a Godsend when I needed to transcribe the endless, narcissistic meanderings of various athletes. A nice tool for the toolbox, but rather flawed.
Indeed, when people, especially other writers whine and complain about the accuracy of their cellphones’ voice transcriptions, I keep mum and shake my head. The very fact that cellphones can come even close to understanding regular speech is actually quite awesome. Anyway, I’ve just had access to a new generation of SRS and even though it’s still not quite state-of-art, I’m impressed. Actually, there already is some built-in recognition software feature on many of the latest Mac and Windows computers, although few people use it.
Then there’s Nuance. Sold separately, just like Dragon NaturallySpeaking for the PC, and Dragon Dictate for the Mac. You probably haven’t heard of it because Nuance spends next to no money selling its products. They are they biggest and best manufacturer of speech-recognition services to companies like Apple, for the iPhone’s dictation feature.
Dragon NaturallySpeaking, for Windows, is almost freakishly fast and accurate, I use it and I feel like I may have sold my soul to the devil. It’s so good that in the latest versions, 11 and 12, you don’t even have to train it by reading a few minutes’ worth of prepared text, so the software can learn how you speak. You just start the baby up and begin dictating. Both Mac and PC versions are fast and accurate; I can dictate hours of stories and poetry and other difficult stuff and create page upon page without locating a single transcription mistake.
Unfortunately, the Mac version, Dragon Dictate, is not quite as clever as the Windows version. Its ‘Full Text Control’ performance is not quite perfect yet. For example, when you’re typing and you want to change something you said three paragraphs back, ‘Full Text Control’ lets you say, “Select “the virgin is in the barn””’ and the Dragon software highlights that phrase, several paragraphs back. That’s ‘Full Text Control’: The dictation software can “read” and jump around in your document just as easily as you can.
Unfortunately, If you fix the error and tell it to go “Go back,” then the software walks the insertion point forward again to the point where you first stopped. Like as not, if you happen to have clicked elsewhere since you typed, forget it! You’ve broken the connection so that the dictation software no longer has any idea where it is in your document.
In Windows, you get ‘Full Text Control’ in all kinds of programs: Internet Explorer, Firefox, Outlook, Word, Notepad, WordPad, OpenOffice Writer, WordPerfect, and Excel.
On the Mac, the list is much shorter: Notepad, TextEdit, Microsoft Word 2011, and Pages 4.3. It’s not in any email programs, unless you happen to use Gmail on its website. Dragon Dictate 4 includes a plug-in that gives you Full Text Control there.
The Mac version does offer any huge new feature that the Windows version doesn’t have: It can transcribe the audio recordings of total strangers. You can feed it MP3 files of speeches, college lectures and Q&As, interviews… and Dragon Dictate will turn it into typed text. To set it up, you create a new “profile” in a voice file, just as you would set up Dictation. Then you open the recorded audio file. Dictate then spends about a minute transcribing the first 60 seconds of the recording before it asks you to read it for corrections. Once that’s done, you are all set. Having tested it, I assure you that it is extremely accurate.
I would add two negative caveats, however. It will not work in conference calls. The machine will simply become confused. They are, I was told at the CES, working on that right now. Also, you can’t highlight the address bar by voice to dictate or type a new web address. You have to use the mouse or the keyboard for that. A lot of good stuff. A few awkward bugs. If it’s not necessary as the bread and butter of your job, maybe wait for the next version…