This tutorial will show you how to enable or disable online speech recognition services for your account or all users in Windows 11.
Microsoft provides both a device-based speech recognition feature and cloud-based (online) speech recognition technologies.
Turning on the Online speech recognition setting lets apps use Microsoft cloud-based speech recognition.
When you use cloud-based speech recognition technologies from Microsoft—whether enabled by the Online speech recognition setting or while you interact with HoloLens or voice typing—Microsoft collects and uses your voice recordings to provide the service by creating a text transcription of the spoken words in the voice data. Microsoft will not store, sample, or listen to your voice recordings without your permission.
You can use device-based speech recognition without sending your voice data to Microsoft. However, the Microsoft cloud-based speech recognition technologies provide more accurate recognition than the device-based speech recognition. When the Online speech recognition setting is turned off, speech services that don’t rely on the cloud and only use device-based recognition—like the Narrator app or the Windows Speech Recognition app—will still work, and Microsoft won’t collect any voice data.
Windows 11 is transitioning from Windows Speech Recognition (WSR) to voice access. WSR is being deprecated. A dialog will pop up when WSR is opened directing you to try voice access and Microsoft has also added a banner under Settings > Accessibility > Speech as well. Voice access, is Microsoft's new assistive technology in Windows 11, uses on-device speech recognition, enabling control of your PC and authoring text without an internet connection. It will support multiple languages and custom commands in a future update (these features are now available for Windows Insiders to try in the Dev and Beta Channels). Microsoft recommends WSR users try and start using voice access today.
References:
Speech, voice activation, inking, typing, and privacy - Microsoft Support
How does Microsoft protect my privacy while improving its speech recognition technology? - Microsoft Support
- Option One: Turn On or Off Online Speech Recognition for Current User in Settings
- Option Two: Turn On or Off Online Speech Recognition for Current User using REG file
- Option Three: Enable or Disable Online Speech Recognition for All Users in Local Group Policy Editor
- Option Four: Enable or Disable Online Speech Recognition for All Users using REG file
1 Open Settings (Win+I).
2 Click/tap on Privacy & security on the left side, and click/tap on Speech on the right side. (see screenshot below)
3 Turn On (default) or Off Online speech recognition for what you want. (see screenshots below)
4 You can now close Settings if you like.
1 Do step 2 (on) or step 3 (off) below for what you want.
This is the default setting.
(Contents of REG file for reference)
Windows Registry Editor Version 5.00
[HKEY_CURRENT_USER\Software\Microsoft\Speech_OneCore\Settings\OnlineSpeechPrivacy]
"HasAccepted"=dword:00000001
(Contents of REG file for reference)
Windows Registry Editor Version 5.00
[HKEY_CURRENT_USER\Software\Microsoft\Speech_OneCore\Settings\OnlineSpeechPrivacy]
"HasAccepted"=dword:00000000
4 Save the REG file to your desktop.
5 Double click/tap on the downloaded REG file to merge it.
6 When prompted, click/tap on Run, Yes (UAC), Yes, and OK to approve the merge.
7 You can now delete the downloaded REG file if you like.
You must be signed in as an administrator to use this option.
The Local Group Policy Editor is only available in the Windows 11 Pro, Enterprise, and Education editions.
All editions can use Option Four to configure the same policy.
1 Open the Local Group Policy Editor (gpedit.msc).
2 Navigate to the policy location below in the left pane of the Local Group Policy Editor. (see screenshot below)
3 In the right pane of Regional and Language Options in the Local Group Policy Editor, double click/tap on the Allow users to enable online speech recognition services policy to edit it. (see screenshot above)
4 Do step 5 (enable) or step 6 (disable) below for what you want.
This is the default setting to allow using Option One and Option Two.
This will override and prevent using Option One and Option Two.
7 You can now close the Local Group Policy Editor if you like.
You must be signed in as an administrator to use this option.
1 Do step 2 (enable) or step 3 (disable) below for what you want.
This is the default setting to allow using Option One and Option Two.
(Contents of REG file for reference)
Windows Registry Editor Version 5.00
[HKEY_LOCAL_MACHINE\SOFTWARE\Policies\Microsoft\InputPersonalization]
"AllowInputPersonalization"=-
This will override and prevent using Option One and Option Two.
(Contents of REG file for reference)
Windows Registry Editor Version 5.00
[HKEY_LOCAL_MACHINE\SOFTWARE\Policies\Microsoft\InputPersonalization]
"AllowInputPersonalization"=dword:00000000
4 Save the REG file to your desktop.
5 Double click/tap on the downloaded REG file to merge it.
6 When prompted, click/tap on Run, Yes (UAC), Yes, and OK to approve the merge.
7 You can now delete the downloaded REG file if you like.
That's it,
Shawn Brink