How to do Real Voice Dictation on iPad

Greetings from the future.

For those of you who don’t know, I’m a big fan of speech recognition software. In particular, I especially like MacSpeech Dictate. I’ve used it successfully to dictate numerous help files, letters, reports, and even a complete 500 page book, Cocoa Touch or IPhone OS 3 . I’m even using it to dictate my next book, Objective-C Developer Reference .

For the most part, I find MacSpeech Dictate’s accuracy to be excellent. Though you have to teach yourself how to dictate to the computer, once you learn how to do it, you can dictate quite quickly.

Perhaps the most difficult part of learning to dictate to the computer is in learning to think your sentences through completely before speaking to the computer. It’s surprising how difficult this is to do in practice.

That said, just being able to use dictation software in general is futuristic. It’s amazing to think that we have the technology available today that I can sit and talk to my computer and it will actually type exactly what I’m saying with outstanding accuracy.

What would make it even more futuristic and more amazing would be if I could be freed from being tethered to my computer. If I could sit in my easy chair, for example, holding a Star Trek like pad in my hands with a direct link to my computer. Dictating my sentences to it and verifying on the screen in my hand that the computer was hearing me correctly. Imagine being able to walk around your house, talking into the air, and having your computer follow every word!

Well, I can tell you, the future is now. I am able to do this today using a combination of three technologies.

The Main Computer

The first, of course, is my MacBook Pro, running MacSpeech Dictate. Typically, I dictate directly into the MacSpeech notebook application. I do this, because the notebook application is able to better cache and track my dictation than if I were dictating directly into a third-party application.

When I’m finished dictating a section of my book, I copy and paste the text from the notebook application into Scrivener.

This works very well for most of my writing needs. The only exception, of course, is that it doesn’t necessarily know many of the specific technical terms that I need to dictate as part of the technical books I’m writing. Fortunately, the MacSpeech Dictate dictionary is easy to customize, allowing me to add whatever specific terms it doesn’t have that I may require. I don’t always do this, because sometimes it’s easier to just type the term into the document and go along my merry way. I usually only modify the dictionary in cases where I’m going to be reusing the term over and over again.

The Comm-Link

The second technology that I use to enable this workflow is a wireless headset by Plantronics. I use the Plantronics Audio 995 Wireless model of headset. It does a pretty decent job. When I bought it, it was the only wireless model my local store had. I see now that Plantronics has many other wireless headsets, so I’d definitely investigate, and perhaps choose a smaller model if I was buying again today.

My only complaints with it, are that it’s a little bit tight around my ears, and the frequency that it uses occasionally interferes with my household wi-fi. The WiFi problem is not one that comes up very often, and the ear tightness I solve by simply hanging the headphones around my neck rather than clamping them over my ears. I don’t actually care about hearing anything from the computer, so I’m actually simply using it as a wireless microphone.

The Handheld Pad

The last and coolest part of this trio of technologies, is my iPad. I use it to watch the screen of my MacBook Pro so that if I need to make any corrections, I can do it as I go. The application that I use to view my MacBook Pro screen is a decent VNC program called Mocha VNC . I chose this particular VNC app because it has a “view only” mode which I like. I enable view-only so that if I accidentally touch the screen, it doesn’t deselect the dictation window.

This combination of technologies enables me to sit anywhere I want, anyway I want, dictate to the computer, and verify that the computer is taking my dictation correctly. I don’t even have to be in the same room as my computer. I can even go sit outside if I want to.

It is, to steal a term from Steve Jobs, magical.

Summary

It’s amazing to think that some of the futuristic technologies that science-fiction authors of the last century only dreamed about have become a reality today.

Truly, we live in the future. But now the next question is, where do we go from here? We have incredible enabling technologies at our fingertips! What are you creating with them?

Posted On 2010-04-17 08:46:00 UTC by Jiva DeVoe
Back
Comments: