Friday, February 10, 2023

What is speech recognition software?

 

For those of you who are new to this rabbit hole of hands-free typing, speech recognition software is defined as assistive technology that allows you to control a computer with voice commands. The apps can either be third-party or built into a computer operating system. Let’s start with the two built in apps first: Windows Speech Recognition (PC) and Voice Control (Mac). Both can be used to open programs, menus, dictate text, and click objects on a computer screen by voice. These built in apps will also give some limited positioning of the mouse using the Grid commands. However, grid commands are very slow for positioning a mouse. I personally hate those commands in any type of app.

There are a lot of speech to text apps available. However, the 4 third-party apps that allow the most complete control of the computer are as follows: Dragon, Talon Voice, Dragonfly, and Serenade. There are people who use more than one of these apps depending on their workflow. Serenade and Dragonfly are open source and free. Talon is proprietary and free although you can become a patron and get beta access to new features and a VIP Slack channel. Talon and Serenade seem to be the most popular of the coding required apps. I have not used these 3 apps because I prefer not to code. So, I can’t speak from experience. I use Dragon, a more “out-of-the-box” app that does not necessarily require coding. An individual license for Dragon ranges anywhere from $150-$699 depending on the software version and type of license. A subscription to Dragon Anywhere starts at $150 per year. I paid $500 for my Dragon Professional license (version 15.61). Let’s say I had some sticker shock. Prior to my injury, I bought the cheapest software and computer that I could find. Those days are over. Between my current software, computer, and other assistive tech, I’ve definitely gone into the thousands.

*Update 4/7/23. A fabulous reader pointed out that Talon is proprietary, not open-source. Thanks Spud! I have made the correction and also per Spud, I am adding Numen, an open source Linux based speech recognition app, to this list.

Not a fan of Windows Speech Recognition or the Dictate function in Word 365

  I was hopeful. But after 3 months of use, I can say that I’m not a fan of either Windows Speech Recognition or the Dictate function in Mic...