Disable Online Speech Recognition via Regedit

This guide explains how to disable Microsoft’s online speech recognition data collection in Windows using the Registry Editor (Regedit). Modifying these registry keys ensures that voice data is processed locally rather than being sent to cloud servers, enhancing your system’s privacy.

Step-by-Step Instructions

Step 1: Open the Registry Editor

  1. Press Windows Key + R to open the Run dialog box.
  2. Type regedit and press Enter.
  3. Click Yes if prompted by User Account Control (UAC).

Step 2: Navigate to the Speech Privacy Key

In the address bar at the top of the Registry Editor, paste the following path and press Enter:

HKEY_CURRENT_USER\Software\Microsoft\Speech_OneCore\Settings\OnlineSpeechPrivacy

Step 3: Modify the Privacy Setting

  1. In the right pane, locate the DWORD value named HasAccepted.
  2. If HasAccepted does not exist:
    • Right-click in an empty area of the right pane.
    • Select New > DWORD (32-bit) Value.
    • Name it HasAccepted.
  3. Double-click HasAccepted to open its properties.
  4. Set the Value data to 0.
  5. Click OK.

Disable via System Policy (All Users)

To enforce this setting system-wide across all user accounts, you can configure the policy key:

  1. In the Registry Editor, navigate to: HKEY_LOCAL_MACHINE\SOFTWARE\Policies\Microsoft\InputPersonalization
  2. If the InputPersonalization key does not exist under Microsoft:
    • Right-click the Microsoft folder.
    • Select New > Key and name it InputPersonalization.
  3. Inside the InputPersonalization key, right-click the right pane and choose New > DWORD (32-bit) Value.
  4. Name the value AllowInputPersonalization.
  5. Double-click AllowInputPersonalization and ensure its Value data is set to 0.
  6. Click OK.

Step 4: Restart Your Computer

Close the Registry Editor and restart your computer to apply the changes. Online speech recognition services will now be disabled.