Speech Recognition not Working Windows 10

Speech Recognition not working on Windows 10. Started trying to use it with Windows update 1903. Omen 17T using Realtek internal microphone. Cortana works, but speech recognition does not. Updated microphone driver, ran it in Administrator mode, tried turning off Cortana. Next plugged in a Dragon Diction Microphone changing appropriate settings and speech recognition would still not work. Note the speech recognition setup about Peter worked in both cases, but after that speech recognition does not do anything when it says it is listening to commands. I troubleshooted with Omen tech support and no luck. Also rolled back Windows to 1809 earlier build, trying everything above again and it still did not work. I would like to be able to use speech recognition with the Realtek internal microphone. Please provide instructions to fix for 1809 build. This feature would be great to help ameliorate repetitive motion injury to wrist and thumb.

Replies (11) 

* Please try a lower page number.

* Please enter only numbers.

* Please try a lower page number.

* Please enter only numbers.

Hey Tucker. I’m Greg, an installation specialist, 10 year Windows MVP, and Volunteer Guardian Moderator here to help you.

Did this work correctly before on the PC? Can you System Restore to a point before the problem began following this guide: http://home.bt.com/tech-gadgets/computing/how-t.

You can System Restore from Repair Mode if it will not work in Windows, following one of these paths: https://www.tenforums.com/tutorials/2294-advanc.

It would be best to try Troubleshooting it first with Version 1903 since you need the Version Update anyway and have me here to help you. But you can try with 1809 first;

When ready I would manually upgrade to the latest version 1903 by opening the Media Creation Tool from this link: http://windows.microsoft.com/en-us/windows-10/m. , choose Download Tool Now, then open the tool and choose Upgrade This PC Now. This saves your files, apps and most settings in place, is the most stable method to change versions, brings your Updates current, resolves most problems.

If any problems report back the verbatim error and number, then continue with these steps for overcoming Version Upgrade problems: http://answers.microsoft.com/en-us/windows/wiki.

If the Version has problems I will work with you to try to resolve them. If the problems are unfixable for now, you have ten days to roll it back in Recovery settings.

Most problems are resolved by doing this gold standard Clean Install which should get you past all difficulties as it has millions of others who have followed the steps in this link and never come back to report another problem: http://answers.microsoft.com/en-us/windows/wiki. . So read it over and see if its something you want to learn to do.

I hope this helps. Feel free to ask back any questions and keep me posted. If you’ll wait to rate whether my post helped you, I will keep working with you until it’s resolved.

I hope this helps. Feel free to ask back any questions and keep me posted. If you will wait to rate my post, I will keep working with you until it’s resolved.

Standard Disclaimer: There are links to non-Microsoft websites. The pages appear to be providing accurate, safe information. Watch out for ads on the sites that may advertise products frequently classified as a PUP (Potentially Unwanted Products). Thoroughly research any product advertised on the sites before you decide to download and install it.

Windows MVP 2010-20

Over 100,000 helped in forums in 10 years
I do not quit for those who are polite and cooperative.
I will walk you through any steps and will not let you fail.

Windows Speech Recognition is lousy in Windows 10

Original title: Speech to text: Cortana much better than Speech Recognition

Cortana translates my speech to text quite well, but Windows Speech Recognition is lousy. It is all Microsoft! Why doesn’t Microsoft share technology so we can have an effective way to dictate into Word Docs? Through our phones, we can all dictate our emails and texts and docs through Siri and Google just fine. Why the delay with Microsoft? or have so many of us just not found out how yet?

Replies (37) 

* Please try a lower page number.

* Please enter only numbers.

* Please try a lower page number.

* Please enter only numbers.

Thank you for posting your query in Microsoft Community. We are glad to help you.

Windows Speech Recognition has been included in Windows 10 with advanced feature of Dictation into applications that weren’t supported previously with Windows 7.

Windows Speech Recognition recognizes your speech accurately and empowers users to interact with their computers by voice. It was designed for people who want to significantly limit their use of the mouse and keyboard while maintaining or increasing their overall productivity. You can dictate documents and emails in mainstream applications, use voice commands to start and switch between applications, control the operating system, and even fill out forms on the Web.

Refer below article to Use Speech Recognition:

Note: The above link applies to Windows 8 but the steps provided can be used for Windows 10 as well.

Hope this information helps. Feel free to get back to us for further queries. We will be happy to assist you.

2 people found this reply helpful

Was this reply helpful?

Sorry this didn’t help.

Great! Thanks for your feedback.

How satisfied are you with this reply?

Thanks for your feedback, it helps us improve the site.

How satisfied are you with this reply?

Thanks for your feedback.

With all due respect to the answer from Jenith, it does not address the problem. I, too cannot get speech recognition to work. I have done all the training, configured microphone, and practiced the speech training over and over, to no avail. If I try using speech recognition for dictation, it simply types gibberish. I speak as distinctly as possible. A simple » The dog is brown» sentence will come out looking like this «axgbfl.» It is not even typing words.

And Cortana is only slightly better. She types words but not the correct one.

Now I tried a simple experiment. I used the google microphone search option and spoke commands and sentences to my computer. Each time the google prompt typed them perfectly, so clearly the microphone is able to hear me just fine.

I did it multiple times, same position in my office chair, same tone of voice. Google worked perfect, Cortana and speech recognition did not.

An example : I tried this same sentence with all three programs.

I said «Start speech recognition».

Google search typed the phrase perfectly.

Cortana typed «Hie Vee invasion»

Speech recognition typed a series of random gibberish letters once again that did not form a word.

I am running windows 10 , all updates installed, computer less than a year old. So what is wrong? It seems like the speech recognition program does not work at all. I have used the older version before on different computers and it usee to work fine.

It is not the microphone as I described, it works fine with other programs.

Cortana sometimes gets it right, but really the misses outweigh the hits and it isn’t worth trying. I need a dictation program and don’t want to pay for one if I can help it, particularly because it seems such a simple thing. My kindle and my Iphone also hear me just fine, right now I am using them primarily instead of my home office computer for dictation which is my temporary answer, but I need to be able to use my computer

Can anyone give an honest solution without referring me to a generic article — is there something corrupted with a file I need to fix?

47 people found this reply helpful

Was this reply helpful?

Sorry this didn’t help.

Great! Thanks for your feedback.

How satisfied are you with this reply?

Thanks for your feedback, it helps us improve the site.

How satisfied are you with this reply?

Thanks for your feedback.

Thank you for your supportive response and verification that it is not just me! Your response will save me (and my wife) a lot of time trying to get my wife to (unsuccessfully) convert over to dictation on her PC. She’ll just keep using Siri on her phone for now, then email her dictation to herself and copy and paste. That will be a lot less work and frustration, even with the extra steps. Thanks again, Ron

(Why on earth can’t a company like Microsoft get it right when Google and Apple can and do?! Microsoft says says it is trying to compete in the mobile and more current scene, but isn’t even close on this basic piece of the action. It would help the productivity and accessibility of their own product, Word, tremendously.)

14 people found this reply helpful

Was this reply helpful?

Sorry this didn’t help.

Great! Thanks for your feedback.

How satisfied are you with this reply?

Thanks for your feedback, it helps us improve the site.

How satisfied are you with this reply?

Thanks for your feedback.

A lot of straying from the original question.

We can dictate to word documents in PC, Office 2013, and phone with Windows 10, the feature is there.

With Windows 10 Mobile phones you can use speech to text for emails and SMS. There is no delay. The phones have the feature right now.

Maybe you haven’t used a Windows 10 phone yet.

Speech recognition works very well on the phone, haven’t used it on the PC much.

6 people found this reply helpful

Was this reply helpful?

Sorry this didn’t help.

Great! Thanks for your feedback.

How satisfied are you with this reply?

Thanks for your feedback, it helps us improve the site.

How satisfied are you with this reply?

Thanks for your feedback.

See, this is the problem. I know how it is SUPPOSED to work, and it just doesn’t. As I stated before, I can get another speech recognition tool on my computer to work perfectly with no fuss whatsoever( google search — it has a speech option). Microphone works just fine for that and the program understands me clearly.

I have tried using WSR multiple times, I know how to start it, I know the command prompts, I know how to use it as I used it on older computers. I know how to speak clearly.

None of these things work. I constantly get helpful hints from it , like «try saying start listening» about 5 times before it will finally kick in. Then, once I get it to finally understand I am dictating and get the program to begin typing, it just types gibberish. Not words, just random letters in a row like this : «xbhfkalopwskghj»

I have even tried speaking single letters clearly, like «A. B. C.» and still will get gkj or some nonsense.

Checked all the settings over and over, it does not work 98% of the time. Every once in a blue moon it will get it right. I have spent hours fussing with it. Cortana is only accurate about 30% of the time. It is NOT user error. I am not a novice at this and like I said, I can get perfect results using google mic on search, so it isn’t a mic error. I have used 4 different microphones as a test. My regular computer one, 2 different headsets, and a high end Yeti. None work with WSR, all work with google.

It has to be a program error. My question is how to fix it. It is obviously faulty software on some systems. If yours works then I am thrilled to know it can work, as I really need it and don’t want to buy Dragon. I just want to know is there a fix.

I know I am not the only one with the problem, and I know my way around a computer, so if there is a patch to fix this I would appreciate someone sharing.

Enable Speech Recognition in Windows 10

Windows provides both a device-based speech recognition feature (available through the Windows Speech Recognition Desktop app), and a cloud-based speech recognition service in those markets and regions where Cortana is available. Here is how to enable the Speech Recognition feature in Windows 10.

Windows Speech Recognition lets you control your PC with your voice alone, without needing a keyboard or mouse. There’s a special wizard to help you get started. You need to plug in your microphone, and then configure Windows Speech Recognition. Speech Recognition is a nice addition to the dictation feature of Windows 10.

Speech Recognition is only available for the following languages: English (United States, United Kingdom, Canada, India, and Australia), French, German, Japanese, Mandarin (Chinese Simplified and Chinese Traditional), and Spanish.

To enable Speech Recognition in Windows 10, do the following.

1. Open the classic Control Panel app.
2. Go to Control Panel\Ease of Access\Speech Recognition.
3. Click on the Start Speech Recognition item.
4. Read the welcome page of the wizard and click on the Next button.
5. Select the microphone type you have connected and click Next.
6. On the next page, click Next to set up your microphone.
7. Read aloud the provided sentence and click Next.
8. Click on the Next button on the next page to confirm the microphone setup.
9. Turn on or off the options Enable document review or Disable document review according to your preferences. You can improve the computer’s ability to recognize spoken words by allowing Speech Recognition to review documents and email in your search index. Speech Recognition will learn words and phrases to better understand you when you speak.
10. Select the option Use manual activation mode or Use voice activation mode. In manual mode, you will need to click on the Microphone icon or press the Ctrl + Win sequence to enable Speech Recognition. In voice activation mode you will need to say the «Start Listening» voice command.
11. On the next page, you can print the list of supported voice commands.
12. On the next page, turn on or off the option Run Speech Recognition at startup for what you want.
13. On the last page of the wizard you can view the tutorial or skip it.

Winaero greatly relies on your support. You can help the site keep bringing you interesting and useful content and software by using these options: