I’ve been experimenting with an application for my iPhone that could be of great help to anyone keeping a blog on the road, as I did last fall on a bicycle ride across the United States.
Son Thomas in Denver, an iPhone user and gadget maven, alerted me to the app “Dragon Dictation,” developed by Nuance.
Once you’ve downloaded and launched the free application, you tap the red dot on the screen and begin speaking — the more distinctly the better.
The app turns the spoken words into a text file, which can then be sent to e-mail, text message, or clipboard — or transferred to another application, such as “Notes.” I e-mailed part of the draft for this blog post to myself, picked up the text and pasted into my blog file.
Even if you enunciate clearly, the text file probably will require some clean-up — usually of punctuation and misspelled words not clearly understood.
I wish I had taken an iPhone, with Dragon Dictation, on my cross-country bike trip. It would have made blogging much easier.
Instead of scribbling into a notebook to recall sights and encounters along the road, I could have dictated into the iPhone and transferred the text files into the blog at the end of the day. After a little editing, the blog post would have been mostly finished.
To me this technology is akin to juju. So I’ll leave the explanation of how it works to Mel Martin, writing on the Web site TUAW, The Unofficial Apple Weblog:
“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.
Martin said he queried Nuance about users’ security because the dictation goes out over the Internet for processing. The reply was as follows:
“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.”