Problem with Voice/language change with pyttsx3

Question

I want to change voice in pyttsx3 module to british male voice, which i do have installed since i can see it in language/speech options and in regedit (Microsoft George), and i do have other voices installed, but when i run this code

i dont see all voices that are on my PC, one of those voices is british male. Out of 9 voices i have, pyttsx3 only recognizes 4 Any fix for that?

Thank you

import pyttsx3
engine = pyttsx3.init()
voices = engine.getProperty('voices')
for voice in voices:
    print("Voice:")
    print(" - ID: %s" % voice.id)
    print(" - Name: %s" % voice.name)
    print(" - Languages: %s" % voice.languages)
    print(" - Gender: %s" % voice.gender)
    print(" - Age: %s" % voice.age)

score 3 · Answer 1 · answered Feb 03 '21 at 10:45

Well it is possible. However you will have to do some changes in registry so proceed below at your own risk. It would be a good practice to backup your registry files or even your system.

STEP 1 Open registry editor:

Press: Windows Key + R and run regedit as administrator.

STEP 2 Check for all the available languages:

You should follow this path: HKEY_LOCAL_MACHINE\SOFTWARE\Microsoft\Speech_OneCore\Voices\Tokens and there you will see all installed voices on your system (except the cortana voices).

STEP 3 Export the voices:

Select the one you want and right click on the folder. For an example: Right click MSTTS_V110_elGR_Stefanos and click export. You can save the file with any name you want but the extension should finish as .reg

STEP 4 Modify the file:

You will need to modify it so that it's values are into two other locations in the registry. Open the file with any text editor of your choice and do the following:

Copy everything except the first line (Windows Registry Editor Version 5.00).
Paste everything at the end of the file.
Modify the location of first data set:[HKEY_LOCAL_MACHINE\SOFTWARE\Microsoft\Speech_OneCore\Voices\Tokens\ MSTTS_V110_elGR_Stefanos(Your voice name here)] to [HKEY_LOCAL_MACHINE\SOFTWARE\Microsoft\Speech\Voices\Tokens\ MSTTS_V110_elGR_Stefanos(Your voice name here)] (Just change the Speech_OneCore to Speech) And that goes to attributes location aswell ...\Speech\Voices\Tokens\(your voice name)\Attributes
Replace the location of the second data set (The one you just copy-pasted at the end) with: [HKEY_LOCAL_MACHINE\SOFTWARE\WOW6432Node\Microsoft\SPEECH\Voices\Tokens\(your voice name)] and it's attributes with [HKEY_LOCAL_MACHINE\SOFTWARE\WOW6432Node\Microsoft\SPEECH\Voices\Tokens\(your voice name)\Attributes

For an example:

Original File:

Windows Registry Editor Version 5.00

[HKEY_LOCAL_MACHINE\SOFTWARE\Microsoft\Speech_OneCore\Voices\Tokens\MSTTS_V110_elGR_Stefanos]
@="Microsoft Stefanos - Greek (Greece)"
"408"="Microsoft Stefanos - Greek (Greece)"
"CLSID"="{179F3D56-1B0B-42B2-A962-59B7EF59FE1B}"
"LangDataPath"=hex(2):25,00,77,00,69,00,6e,00,64,00,69,00,72,00,25,00,5c,00,53,\
  00,70,00,65,00,65,00,63,00,68,00,5f,00,4f,00,6e,00,65,00,43,00,6f,00,72,00,\
  65,00,5c,00,45,00,6e,00,67,00,69,00,6e,00,65,00,73,00,5c,00,54,00,54,00,53,\
  00,5c,00,65,00,6c,00,2d,00,47,00,52,00,5c,00,4d,00,53,00,54,00,54,00,53,00,\
  4c,00,6f,00,63,00,45,00,6c,00,47,00,52,00,2e,00,64,00,61,00,74,00,00,00
"VoicePath"=hex(2):25,00,77,00,69,00,6e,00,64,00,69,00,72,00,25,00,5c,00,53,00,\
  70,00,65,00,65,00,63,00,68,00,5f,00,4f,00,6e,00,65,00,43,00,6f,00,72,00,65,\
  00,5c,00,45,00,6e,00,67,00,69,00,6e,00,65,00,73,00,5c,00,54,00,54,00,53,00,\
  5c,00,65,00,6c,00,2d,00,47,00,52,00,5c,00,4d,00,31,00,30,00,33,00,32,00,53,\
  00,74,00,65,00,66,00,61,00,6e,00,6f,00,73,00,00,00

[HKEY_LOCAL_MACHINE\SOFTWARE\Microsoft\Speech_OneCore\Voices\Tokens\MSTTS_V110_elGR_Stefanos\Attributes]
"Age"="Adult"
"DataVersion"="11.0.2016.1016"
"Gender"="Male"
"Language"="408"
"Name"="Microsoft Stefanos"
"SayAsSupport"="spell=NativeSupported; alphanumeric=NativeSupported"
"SharedPronunciation"=""
"Vendor"="Microsoft"
"Version"="11.0"

Modified registry file:

Windows Registry Editor Version 5.00

[HKEY_LOCAL_MACHINE\SOFTWARE\Microsoft\Speech\Voices\Tokens\MSTTS_V110_elGR_Stefanos]
@="Microsoft Stefanos - Greek (Greece)"
"408"="Microsoft Stefanos - Greek (Greece)"
"CLSID"="{179F3D56-1B0B-42B2-A962-59B7EF59FE1B}"
"LangDataPath"=hex(2):25,00,77,00,69,00,6e,00,64,00,69,00,72,00,25,00,5c,00,53,\
  00,70,00,65,00,65,00,63,00,68,00,5f,00,4f,00,6e,00,65,00,43,00,6f,00,72,00,\
  65,00,5c,00,45,00,6e,00,67,00,69,00,6e,00,65,00,73,00,5c,00,54,00,54,00,53,\
  00,5c,00,65,00,6c,00,2d,00,47,00,52,00,5c,00,4d,00,53,00,54,00,54,00,53,00,\
  4c,00,6f,00,63,00,45,00,6c,00,47,00,52,00,2e,00,64,00,61,00,74,00,00,00
"VoicePath"=hex(2):25,00,77,00,69,00,6e,00,64,00,69,00,72,00,25,00,5c,00,53,00,\
  70,00,65,00,65,00,63,00,68,00,5f,00,4f,00,6e,00,65,00,43,00,6f,00,72,00,65,\
  00,5c,00,45,00,6e,00,67,00,69,00,6e,00,65,00,73,00,5c,00,54,00,54,00,53,00,\
  5c,00,65,00,6c,00,2d,00,47,00,52,00,5c,00,4d,00,31,00,30,00,33,00,32,00,53,\
  00,74,00,65,00,66,00,61,00,6e,00,6f,00,73,00,00,00

[HKEY_LOCAL_MACHINE\SOFTWARE\Microsoft\Speech\Voices\Tokens\MSTTS_V110_elGR_Stefanos\Attributes]
"Age"="Adult"
"DataVersion"="11.0.2016.1016"
"Gender"="Male"
"Language"="408"
"Name"="Microsoft Stefanos"
"SayAsSupport"="spell=NativeSupported; alphanumeric=NativeSupported"
"SharedPronunciation"=""
"Vendor"="Microsoft"
"Version"="11.0"

[HKEY_LOCAL_MACHINE\SOFTWARE\WOW6432Node\Microsoft\SPEECH\Voices\Tokens\MSTTS_V110_elGR_Stefanos]
@="Microsoft Stefanos - Greek (Greece)"
"408"="Microsoft Stefanos - Greek (Greece)"
"CLSID"="{179F3D56-1B0B-42B2-A962-59B7EF59FE1B}"
"LangDataPath"=hex(2):25,00,77,00,69,00,6e,00,64,00,69,00,72,00,25,00,5c,00,53,\
  00,70,00,65,00,65,00,63,00,68,00,5f,00,4f,00,6e,00,65,00,43,00,6f,00,72,00,\
  65,00,5c,00,45,00,6e,00,67,00,69,00,6e,00,65,00,73,00,5c,00,54,00,54,00,53,\
  00,5c,00,65,00,6c,00,2d,00,47,00,52,00,5c,00,4d,00,53,00,54,00,54,00,53,00,\
  4c,00,6f,00,63,00,45,00,6c,00,47,00,52,00,2e,00,64,00,61,00,74,00,00,00
"VoicePath"=hex(2):25,00,77,00,69,00,6e,00,64,00,69,00,72,00,25,00,5c,00,53,00,\
  70,00,65,00,65,00,63,00,68,00,5f,00,4f,00,6e,00,65,00,43,00,6f,00,72,00,65,\
  00,5c,00,45,00,6e,00,67,00,69,00,6e,00,65,00,73,00,5c,00,54,00,54,00,53,00,\
  5c,00,65,00,6c,00,2d,00,47,00,52,00,5c,00,4d,00,31,00,30,00,33,00,32,00,53,\
  00,74,00,65,00,66,00,61,00,6e,00,6f,00,73,00,00,00

[HKEY_LOCAL_MACHINE\SOFTWARE\WOW6432Node\Microsoft\SPEECH\Voices\Tokens\MSTTS_V110_elGR_Stefanos\Attributes]
"Age"="Adult"
"DataVersion"="11.0.2016.1016"
"Gender"="Male"
"Language"="408"
"Name"="Microsoft Stefanos"
"SayAsSupport"="spell=NativeSupported; alphanumeric=NativeSupported"
"SharedPronunciation"=""
"Vendor"="Microsoft"
"Version"="11.0"

STEP 5 Import the file:

Save the file and double click on it. There will be a warning window press yes and proceed.

STEP 6 Check:

run the following code:

engine = pyttsx3.init()
voices = engine.getProperty("voices")

for voice in voices:
    print(voice.id)

Output:

HKEY_LOCAL_MACHINE\SOFTWARE\Microsoft\Speech\Voices\Tokens\TTS_MS_EN-US_DAVID_11.0 HKEY_LOCAL_MACHINE\SOFTWARE\Microsoft\Speech\Voices\Tokens\MSTTS_V110_elGR_Stefanos HKEY_LOCAL_MACHINE\SOFTWARE\Microsoft\Speech\Voices\Tokens\TTS_MS_EN-US_ZIRA_11.0

score 0 · Answer 2 · edited Jun 26 '20 at 09:20

The Microsoft downloadable voices seem to be limited. If you go to their regedit path you'll see that the extra downloadable voices like Microsoft George from the GB package are saved onto a different path than the one that is accepted by pyttsx3.

On top of this, on further examination, when navigating to the path of these voices (Computer\HKEY_LOCAL_MACHINE\SOFTWARE\Microsoft\Speech_OneCore\Voices\Tokens), I noticed that none of these have a tts attribute, like the default David, Zyra, and Iriana do. This leads me to believe that they cannot be used for tts.

score 0 · Answer 3 · answered Jan 13 '21 at 16:02

If you downloaded the language you want to use, it is possible.

Use this way:

Your downloaded languages goes this path in registry: Computer\HKEY_LOCAL_MACHINE\SOFTWARE\Microsoft\Speech_OneCore\Voices\Tokens

Right click to Tokens node then export these languages from this path, save as lang.reg file. Then open lang.reg file with any text editor then replace text "Speech_OneCore" to "Speech" then save and close.

Double click lang.reg file to import.

In your python file, use it as follows:

import pyttsx3
engine = pyttsx3.init()
engine.setProperty('voice',"HKEY_LOCAL_MACHINE\SOFTWARE\Microsoft\Speech\Voices\Tokens\MSTTS_V110_trTR_Tolga")
engine.say(text="Merhaba dünya")
engine.runAndWait()
# to save to a file
# engine.save_to_file(text="Merhaba dünya", filename="file.mp3")

Problem with Voice/language change with pyttsx3

3 Answers3

Linked