In the early days of speech recognition, you’ll be lucky to get half of your words, even if you speak as slowly as a robot. Today, every smartphone has some sort of voice assistant that can quickly take notes for you or perform tasks like opening apps.
However, if you have a Windows 10 computer, you can also control Windows 10 with your voice. This is not just a cool feature. It can be a real productivity booster and, for people with certain disabilities, an effective way to take control of their computer.
Control and Spelling
Do you want to control Windows 10 with your voice, or do you simply want it to record what you say? Voice control is a different function than dictation and some users often get confused between the two concepts. If all you want to do is simply speak and let the computer write what you say, you don’t need to make all the effort to set up speech recognition.
For example, Google Docs has great voice dictation that uses the power of the cloud to turn your speech into text. If you are a macOS user, you can even use integrated system.
This article is about voice control, rather than voice dictation. In other words, we want to use Windows and complete common tasks without using a keyboard or mouse.
Choose the right microphone
If you want to control Windows 10 with your voice, you need to give your computer some way to hear you. If you’re using a laptop or have a desktop webcam, you already have a basic microphone at hand, but they don’t always work well for speech recognition.
Since you already have these microphones, you can’t try voice control with them, but a better microphone would certainly make things better. We are using a Samson Go microphone here.
Tell Windows which Mic to use
Before you can start giving commands to your computer, you need to specify the microphone it should use. Since Windows supports multiple mics at the same time, it can sometimes choose one mic as default which is not optimal for voice control.
Once you’ve plugged in your microphone (assuming it’s an external microphone), it’s pretty easy to select it as your active recording device. Just right-click the speaker icon in the system tray.
Then click Open Sound Settings.
In the Pop-up, under “input,” select the microphone you want the system to use from the drop-down list.
Set up voice recognition
To start the process of activating speech recognition on your Windows 10 computer, open the Start Menu and type Voice recognition. Then open it up.
In the New Window that appears, click Start voice recognition. You may get a pop-up warning that speech recognition is optimized for US English speakers. Just click OK to remove this.
Next, you’ll see this wizard, which will guide you through the setup process.
Next, you need to choose the type of microphone you are using. We’re using a Samson Go microphone placed on a desktop (or clipped to a monitor) so we’ll choose Desktop microphone.
The next screen will guide you through setting up the microphone. It’s different for each type of mic, so we won’t show that here.
Now read the sample text to help Windows calibrate your microphone.
If the computer understands you enough, you can click next..
You should now see an option to let Windows read through your document, to understand your vocabulary and expressions. Do you want to do that or not. If you have material with unrelated content or have privacy concerns, please disable this feature.
OK, we’re almost done. Now all you have to do is choose your activation mode.
Basically, you need to decide if you want to enable speech recognition by speaking a keyword, meaning it always sounds good via a keyboard shortcut.
Now you have the opportunity to print out a reference card with the usual commands.
Honestly, most people won’t need this since you can always look up commands when you need to, but if you’re preparing the computer for users with disabilities or less tech savvy, this Very convenient to print out and store up close. calculator for reference.
Finally, after choosing whether or not to run speech recognition at startup, you will be given the option to go through the instructions. If you haven’t already, you should! For those who have gone through the tutorial, just skip it.
When speech recognition is running, you’ll see this on your screen.
Enable speech recognition using your chosen activation method, although Windows Key + Ctrl will act as a toggle regardless. As a test, just say Start Menu with the “listen” indicator turned on. The Start menu will pop up immediately. Refer to the official reference tag for more commands.
With the basic setup complete, you’re ready to control your computer with just your voice. However, you may want to train Windows more to make speech recognition more accurate. You’ll find the training app in the speech recognition settings that you first used to set up speech recognition.
The more voice samples WINdows has, the better the system will perform. That being said, if you get a lot of missed or misheard commands, take a few minutes to train your speech recognition system.
Cortana and third-party options
It’s great that Windows 10 comes with a built-in speech recognition app to control Windows 10 with your voice, but is there a better alternative? The truth is that voice control on the desktop is a pretty niche area. It is generally considered an accessibility feature. So there aren’t many third-party options.
Interestingly, Windows 10 has a completely separate voice activation system in the form of Cortana. As a voice assistant, Cortana is not designed to be a voice-based replacement for the keyboard and mouse, but there is quite a bit of overlap between the two systems. Take a look at what Cortana can do, which might be better suited to your specific needs than a general-purpose speech recognition system.
As for third-party voice control, there’s not much there. The biggest name at the moment is Dragon Voice Recognition from Nuance. They are the leaders in computer speech recognition and perhaps the most experienced of any company in the field. This is an option worth exploring if you have complex or mission-based speech recognition needs.