Science fiction writers have long imagined a future where we simply voice-command our devices, cars or spaceships. The technology isn’t quite there yet, despite Apple’s best efforts with Siri, its digital personal assistant.
But our smartphones and tablets are getting quite good at turning the spoken word into text. This app technology has the power to turn your mobile device into a powerful writing tool, without your having to lift a stylus or type on a touch screen.
Dragon Dictation, a simple speech-to-text app that is free on iOS, is probably the best-known. On the left of its main page is a list of Notes you’ve previously entered; on the right is a larger section where you enter or view text inside notes.
At the top of the main section is a red Record button. The app records for as long as necessary, showing the audio level of your voice as a graph at the bottom of the screen. Tapping anywhere on the screen turns off recording, or you can adjust the app to automatically detect when you’ve stopped speaking.
The app sends a digital sample of your speech over the Internet to do the speech recognition, so it requires a wireless connection. But this process is speedy, and the app soon displays your transcribed text in the main window. Naturally, it doesn’t get all the words right, perhaps because you mumbled or made some other mistake, but you may be surprised at how accurate it is overall.
For example, it successfully transcribed “I read the red book,” even though “read” and “red” are pronounced the same. Fixing or editing text is easy. Tap on a word, and the app gives you the option to delete it or bring up an on-screen keyboard for manual corrections. When you are satisfied, the app can send the text by email or share it on Facebook or as a Twitter post.
Although the app works very well, I’ve found that using a plug-in microphone with it provides the best speech recognition.
The need to be connected to the remote recognition system could lead to expensive network charges if you use the app frequently over 3G or 4G.
Listnote Speech/Text Notepad is a similar Android app, available as an ad-supported free download. Like Dragon, the app’s main interface revolves around your list of previous notes. These can be organized by categories. To create a speech note, you tap on the large Speech Recognition button at the top of the app, and then speak. Translated text quickly appears in the relevant space in a new Note section on the screen.
If the text wasn’t quite what you said, tap on the arrow icon near the text and select from a short list of other guesses. Alternatively, you can edit the text manually by long-pressing on it. Conveniently, the app lets you pause in midspeech and offers a Continue Speech button.
Among its weaknesses is a confusing menu system; at first you may not realize how to add a note in a category, and it is not obvious that you must press the big Speech Recognition box to begin recording.
Android’s speech recognition can also be quirky. For example, I tried dictating lyrics to the classic British song “I Do Like to Be Beside the Seaside,” thinking the words would confuse the app. But I omitted the word “oh” from a verse, and yet the app inserted it for me anyway.
A different speech-to-text app on iOS is the free PaperPort Notes. This is a much more sophisticated notes-managing app that can also handle embedded photos and hand-scribbled notes. It also has “image to text” functions to recognize printed text, but only if you’re prepared to sign up for a free account.
The app has complex editing powers, such as embedding faux Post-it notes, and you can change the color of text. With all these functions, PaperPort will probably appeal to students or business users.
The app does a good a job of recognizing speech, and I really wanted to love it, but it’s tricky to use. The interface isn’t intuitive, and it’s easy to accidentally brush a part of the screen that activates one of the controls.
Apple, Google and Microsoft all now offer direct speech-to-text recognition in their mobile operating systems, and you can use those features wherever there is an option to type in text. Apple’s is perhaps the most intuitive to use, although Google has put a similar function into Android. It’s easy to forget that your devices have this functionality built in, and it’s worth exploring how reliable or useful it can be for you.