Filed under: Analysis / Opinion, Odds and ends, iPhone, App Review
Dragon Dictation comes to the iPhone. Wow.
Put this into the 'I didn't think they could ever get this to work on an iPhone' category. I'm talking about Dragon Dictation [iTunes link] from Nuance, the developers of the very popular Dragon Naturally Speaking for the PC. Nuance also provides the speech recognition engine for MacSpeech Dictate on the Mac platform.
To dictate on the iPhone you just launch the app, press the record button, and start talking. Your dictation can be a brief sentence, or a much longer treatise. Once the text has been created from your speech, it's possible to email it, send it as a text message, or put the result in your clipboard. After recording your message, you can edit the resulting text before you send it off for others to read.
It's pretty slick! When you record your message, it is quickly transmitted to Nuance servers where a speech recognition algorithm is run against your data. The resulting text is returned to your iPhone very quickly; my informal benchmarks showed that it took about a second for text to be processed on a Wi-Fi network, and less than 5 seconds over 3G. You'll need a data connection for the app to work, but having this speech-to-text capability is going to be very important to a lot of people, who will find all sorts of uses for it.
I tested the app for about a week and found the accuracy to be very good. Accuracy diminishes if you are in a very noisy environment, as I found when I tried some dictation while being driven down the interstate. There were a few errors, but they were easy to correct. To add punctuation to your text, you can say 'period', 'question mark', or 'new paragraph,' and Dragon Dictation adds the appropriate punctuation.
Since your dictation goes out over the internet for processing, I asked Nuance about security. Their reply was as follows:
How much will this capability cost? Nothing. For a limited time Dragon Dictation is absolutely free, but at some point there will be a charge for it. I spoke to Michael Thompson, senior vice president and general manager for Nuance Mobile, and he said they see all sorts of specialized applications of this technology, such as in the legal and medical professions. The app has gone live and is available now."Search queries and dictation requests are transcribed by fully automated speech recognition software, without the use of humans. Data is uploaded and collected in order to improve performance for individual users, and to improve the general performance of the system.
All speech recognition requests and associated data are processed in data centers in the U.S. that meet stringent security and privacy standards; these are the same standards that we use for processing private information in other areas of our business."
![TUAW [Cafepress]](http://www.blogsmithmedia.com/www.tuaw.com/media/tuaw-cafepress-promo.png)
Reader Comments (Page 1 of 4)
Ryan said 12:23AM on 12-08-2009
thanks for that!! what a cool app. i like that if it dictates incorrectly, you can tap on the word for suggestions. so far, when it has been incorrect for me, the suggestions have been accurate.
Reply
Intarweb User said 12:44AM on 12-08-2009
From the Terms Of Service:
3.3. NAMES AND SPEECH DATA. As part of the Service. Nuance collects and uses: (1) the names of individuals in your address book...
Not familiar with Dragon/Nuance, but that takes a little trust.
Reply
gtdavemac said 1:10AM on 12-08-2009
Collects names? Big deal.
If I had to guess, it seems like this will help the app properly recognize the names of people in your contacts, since you are likely to speak about them.
Todd Sieling said 12:51AM on 12-08-2009
I'd guess the address book info is collected to correlate with spoken names and addresses and maybe link them? Nonetheless it would be good if they spelled out what they do and don't do with that data, though isn't that part of what the app store review process watches for?
Aside, yes the not-in-Canada store is lame. Hopefully just a delay, but if a store-switcheroo it takes...
Jonathan said 9:13AM on 12-08-2009
A lot of cell phones use Nuance for their voice dialling. Blackberry, Nokia, and Motorola all do, at the very least.
JD said 3:40PM on 12-08-2009
I read elsewhere that it also retains a copy on their servers of everything you've ever transcribed, available to the gov't indefinitely. I know, I know, if you have nothing to hide, why fear more surveillance...
Roger said 5:16PM on 12-08-2009
Very disappointing, this part about not only reading your contact info, but asking you to sign on in giving it to your service provider, authorities with or without a warrant, etc. If it is only to aid transcriptions of names, which admittedly can be tough for this kind of application, how about at least an opt-out, with the user acknowledging and accepting that names may possibly spelled incorrectly?
Howard Hudson said 1:59AM on 12-09-2009
Access to my contacts IS a big deal. It may be a breach of attorney-client confidentiality (Oregon Rules of Professional Conduct 1.6(a)
"(a) A lawyer shall not reveal information relating to
the representation of a client unless the client gives
informed consent, the disclosure is impliedly authorized
in order to carry out the representation or the disclosure is
permitted by paragraph (b)" [Convenience isn't one of the exceptions...]
The last time I checked, the mere fact that the client is represented meets the "information relating" test.
As an attorney who would LOVE to have this product on the iPhones in my firm, it is a non-starter for me.
Pity.
Scott McLeod said 12:44AM on 12-08-2009
Not available in Canada.
WTF Guys, seriously. We're your damn neighbors. Why the tall fence?
If I have to pay for this by the time it's released up here, it kinda defeats the purpose of being an "early adopter."
I bought it on my American iTunes account, but syncing is going to be a PITA.
Reply
Martin said 2:11AM on 12-08-2009
For what it's worth, paying more is exactly what being an early adopter is all about.
Todd Sieling said 12:44AM on 12-08-2009
Knock Knock
Who's there?
The future yo'!
Seriously, that is really cool.
Reply
Noah said 12:56AM on 12-08-2009
Hot damn. I'm already finding this app super useful!
Reply
Marko said 1:03AM on 12-08-2009
reQall is free and has had speech-to-text feature for a long time (and much more). http://www.reqall.com/
Reply
caleb roberts said 1:06AM on 12-08-2009
No iPod Touch support. Lame...
Reply
Cy Starkman said 1:05AM on 12-08-2009
Not in the Australia store...
and personally, i'm thankful, i'm spared the inevitable disappointment from discovering that Nuance still thinks the entire world speaks like someone from New York.
They make great stuff, for Americans.
Reply
Sam said 1:39AM on 12-08-2009
Really? I use Naturally Speaking 10.1 on Windows for work with dialect set up for Australian. I don't speak like a bogan, but I do have the lovely Australian drawl. Straight from the box it was 80% accurate, with training its now about 90%+ accurate.
Far better than the iPhone's built-in voice control which doesn't understand me unless I pretend I'm from Texas...
Cy Starkman said 7:58AM on 12-09-2009
Perhaps they have improved, totally plausible.
You have trouble with voice control on iPhone? Hmmm
if nothing else this all tells me we have a way to go. I still wonder why they don't use the network to expand it's recognition as opposed to an algorithim on a remote fast server. You know it could be accumulating nuances from the input of maybe millions of users
A.J. said 5:15PM on 3-06-2010
Well that's to be expected. You Aussies are cute, but you sure Tawk funny.
Just_a_guy said 1:08AM on 12-08-2009
What's the difference between this and Vlingo?
Reply
Anthony said 1:23AM on 12-08-2009
Wow?? Firstly there's an app that already does this called Voxie. Secondly it would only be "wow" if it did it without sending it off to a server.
Reply