Wednesday, May 18, 2016

Nuance Vocalizer Expressive TTS 5.4

Nuance Vocalizer Expressive TTS 5.4
Nuance Vocalizer Expressive TTS 5.4


Website
vocalizer expressive

System Requirements
OS: Windows Vista - Windows 11 (Vocalizer Expressive 5.2.3 does support Windows XP)
Reading application: any application with SAPI-5 support


Description
Vocalizer Expressive is a text-to-speech engine used by Reading applications to produce speech from electronic text. The voices sound very close to the natural human speech. Some of them, like Spanish Jorge, were first developed by Loquendo and then improved by Nuance.

Incompatibility
The Voices from this release may not function properly if installed on the same computer with the following products: Vocalizer Expressive 5.2.3 (Previous release), kobaspeech.com, harposoftware.com. It's recommended to remove these products before installing Vocalizer Expressive 5.4.

Installation
To install the voices, extract the archive(s) to any folder and run Setup.exe
After installation is complete, Windows Installer will delete files in unpacked folder because it assumes them been temporary. So, unpacked folder will not have any further use and it must be deleted.
The list of voices can be seen in the Speech Properties, which is located under Control Panel, Speech Recognition, Text to Speech.

Uninstallation
To uninstall particular voice go to Start Menu, All Programs, VE 5.4 [Name of Voice], Uninstall.

American English - Allison, Ava, Evan, Joelle, Nathan, Noelle, Samantha, Susan, Tom, Zoe
Arabic - Laila, Maged, Mariam, Tarik
Argentinian Spanish - Diego, Isabela
Australian English - Karen, Lee
Basque - Miren
Belgian Dutch - Ellen
Bhojpuri India - Jaya
Brazilian Portuguese - Felipe, Fernanda, Luciana
British English - Daniel, Kate, Malcolm, Oliver, Serena, Stephanie
Bulgarian - Daria
Canadian French - Amelie, Chantal, Nicolas
Catalan - Jordi, Montserrat
Chilean Spanish - Francisca
Chinese Mandarin - Bin-Bin, Li-Li, Tian-Tian
Colombian Spanish - Carlos, Soledad, Ximena
Croatian - Lana
Czech - Iveta, Zuzana
Danish - Magnus, Sara
Dutch - Claire, Xander
Farsi - Dariush
Finnish - Onni, Satu
French - Audrey, Aurelie, Thomas
Galician - Carmela
German - Anna, Markus, Petra, Viktor, Yannick
Greek - Melina, Nikos
Hebrew - Carmit
Hindi - Lekha, Neel
Hong Kong Cantonese - Sin-Ji
Hungarian - Mariska
Indian Bengali - Paya
Indian English - Rishi, Sangeeta, Veena
Indonesian - Damayanti
Irish English - Moira
Italian - Alice, Federica, Luca, Paola
Japanese - Ayane, Daisuke, Ichiro, Kyoko, Mizuki, Otoya, Sakura
Kannada - Alpana
Korean - Sora, Yuna
Malay - Amira
Marathi - Ananya
Mexican Spanish - Angelica, Juan, Paulina
Norwegian - Henrik, Nora
Polish - Ewa, Krzysztof, Zosia
Portuguese - Catarina, Joana, Joaquim
Romanian - Ioana
Russian - Katya, Milena, Yuri
Scottish English - Fiona
Sichuanese - Fangfang
Slovak - Laura
South African English - Tessa
Spanish - Jorge, Marisol, Monica
Swedish - Alva, Klara, Oskar
Taiwanese Mandarin - Mei-Jia
Tamil - Vani
Telugu - Geeta
Thai - Kanya, Narisa
Turkish - Cem, Yelda
Ukrainian - Lesya
Valencian - Empar
Vietnamese - Linh

American English - Allison, Ava, Evan, Joelle, Nathan, Noelle, Samantha, Susan, Tom, Zoe
Arabic - Laila, Maged, Mariam, Tarik
Argentinian Spanish - Diego, Isabela
Australian English - Karen, Lee
Basque - Miren
Belgian Dutch - Ellen
Bhojpuri India - Jaya
Brazilian Portuguese - Felipe, Fernanda, Luciana
British English - Daniel, Kate, Malcolm, Oliver, Serena, Stephanie
Bulgarian - Daria
Canadian French - Amelie, Chantal, Nicolas
Catalan - Jordi, Montserrat
Chilean Spanish - Francisca
Chinese Mandarin - Bin-Bin, Li-Li, Tian-Tian
Colombian Spanish - Carlos, Soledad, Ximena
Croatian - Lana
Czech - Iveta, Zuzana
Danish - Magnus, Sara
Dutch - Claire, Xander
Farsi - Dariush
Finnish - Onni, Satu
French - Audrey, Aurelie, Thomas
Galician - Carmela
German - Anna, Markus, Petra, Viktor, Yannick
Greek - Melina, Nikos
Hebrew - Carmit
Hindi - Lekha, Neel
Hong Kong Cantonese - Sin-Ji
Hungarian - Mariska
Indian Bengali - Paya
Indian English - Rishi, Sangeeta, Veena
Indonesian - Damayanti
Irish English - Moira
Italian - Alice, Federica, Luca, Paola
Japanese - Ayane, Daisuke, Ichiro, Kyoko, Mizuki, Otoya, Sakura
Kannada - Alpana
Korean - Sora, Yuna
Malay - Amira
Marathi - Ananya
Mexican Spanish - Angelica, Juan, Paulina
Norwegian - Henrik, Nora
Polish - Ewa, Krzysztof, Zosia
Portuguese - Catarina, Joana, Joaquim
Romanian - Ioana
Russian - Katya, Milena, Yuri
Scottish English - Fiona
Sichuanese - Fangfang
Slovak - Laura
South African English - Tessa
Spanish - Jorge, Marisol, Monica
Swedish - Alva, Klara, Oskar
Taiwanese Mandarin - Mei-Jia
Tamil - Vani
Telugu - Geeta
Thai - Kanya, Narisa
Turkish - Cem, Yelda
Ukrainian - Lesya
Valencian - Empar
Vietnamese - Linh


Additional information
On some websites "Vocalizer Expressive TTS 5.4" can be called as "Vocalizer Expressive Version 2", while "Vocalizer Expressive 5.2.3" can be called as "Vocalizer Expressive Version 1". These are essentially the same products, only names are different. All voices have the quality "Premium High", except Bin-Bin, Li-Li, Sin-Ji, Tian-Tian, Fang-Fang which have the quality "Embedded". Here is small file TTSApp.exe, which can be used to check out installed voices. Inside this program the setting "Format" must be set to "22kHz 16 Bit Stereo" for better audio output.

Free software to read text aloud
Claude
NaturalReader
Balabolka
Zabaware TTS Reader
KMPlayer - KMPlayer is a video player with ability to speak subtitles of movies. However, the recent versions of this program have a bug: subtitles are repeated several times. The last version that speak subtitles properly is KMPlayer v3.8.0.120
Daum PotPlayer - PotPlayer is another video player which can speak subtitles of movies. In contrast to KMPlayer the subtitles are pronounced correctly

Screenshots

Balabolka Natural Reader KMPlayer

Edit Pronunciation
The pronunciation of the Voices can be modified by creating "User dictionary". It's binary (unreadable for human) file with name "userdct_xxx.dat", where xxx is abbreviation of a language. Where to get this abbreviation? This abbreviation can be found inside of HDR file of the Voice. The *.HDR files are located inside the "ve" folder of Vocalizer 5.4 installation path. For example, C:\Program Files\VE\languages\enu\speech\ve\ve_pipeline_enu_allison_22_premium-high_1-0-2.hdr. The content of HDR file looks like XML:
<?xml version="1.0"?>
<NUANCE>
<VERSION>NUAN_1.0</VERSION>
<HEADER>
  <BROKERSTRING>pipeline/American English/allison/22/premium-high/text/pcm</BROKERSTRING>
  <PRIORITY>5343</PRIORITY>
  <PARAMETERS>
    <language>American English</language>
    <langcode>ENU</langcode>
    <langid>10</langid>
    <langversion>6.0.9</langversion>
    <nativetypeofchar>utf-16</nativetypeofchar>
    <voice>Allison</voice>

In the above example the abbreviation of language is langcode ENU.
At a present time the file "userdct_xxx.dat" can be created in two ways: with Python and with "Vocalizer Expressive Studio". When using Python, it's necessary to know phonetic transcriptions of words, while adding them to dictionary. In contrast, Vocalizer Expressive Studio automatically generates phonetic transcriptions. However, Vocalizer Expressive Studio works only with "Vocalizer Expressive 5.2.3". Created dictionaries can be used in older and newer versions of Vocalizer (5.2.3 and 5.4). Below I will describe both methods.

Creating user dictionary with Python 2.5.4 and Vocon 3200

This method doesn't require "Vocalizer Expressive" been installed. The voices may not be present on a PC and still, it's possible to create user dictionary for them.
As an example, I will create user dictionary for the Finnish language. In this case the file name of user dictionary would be "userdct_fif.dat". First, create usual text file with similar content:
[Header]
Name=userdct_fif.dct
Description=userdct_fif
Language=FIF
Content=EDCT_CONTENT_BROAD_NARROWS
Representation=EDCT_REPR_SZZ_STRING

[Data]
tuhatvuotta // #te.x:At.vu.ottA#
ikuisuus // #@:nKu&iso:S#

This file must be encoded in UTF-8 without BOM. Here, the Name is the name of text file; Description can be any description; Language is uppercase of abbreviation; tuhatvuotta is the source string with 40 characters maximum length; space plus // plus space is separator; #te.x:At.vu.ottA# is a destination string – it's how the word should be pronounced. Note, the # sign here is the pause (silence). Destination string can only contain phonetic symbols in so called L&H+ (Lernout & Hauspie) notation.
All necessary symbols can be found in four tables of this PDF document. These tables contain all Finnish symbols of L&H+. First is called "Special characters" on page 13, another is "Punctuation Marks" on page 14, third is "The Finnish L&H+ and UNIPA Phonetic Alphabets" on pages 15-16 and the fourth is "SAPI5 Symbols" on pages 18-19. From tables 3 and 4 you'll need only first column.
You can add as many words as you like, but they must be separated by newline (CR+LF). After creating text file, you can save it as userdct_fif.dct.
Now, download python-2.5.4 and VoCon 3200. Install them to some path without spaces such as C:\Python25 and C:\PF\Nuance\vocon3200\EDS3. Create *.bat file with content:
@set in=C:\userdct_fif.dct
@set out=C:\userdct_fif.dat
@set VOCON3200_INSTALL_PATH=C:\PF\Nuance\vocon3200\EDS3
@set MODELLANG=fif
@C:\Python25\python.exe "%VOCON3200_INSTALL_PATH%\tools\dictcpl.pyc" --dictionaryFilepath=%in% --outputFilepath=%out%

Here, C:\userdct_fif.dct is a path to text file, created earlier and C:\userdct_fif.dat is path for output binary file. When you run bat file Python will generate binary dictionary "userdct_fif.dat"

Creating user dictionary with Vocalizer Expressive Studio 1.4.0

This method requires installation of Vocalizer Expressive 5.2.3 voices, for which you intend to create a dictionaries. These dictionaries can also be used by Vocalizer 5.4 voices of corresponding language. If you are going to use this method and you also have Vocalizer 5.4 installed, I recommend to uninstall Vocalizer 5.4 first, or use this method on another PC or in virtual machine.
As an example, I will create user dictionary for the German language. In this case the file name of user dictionary would be "userdct_ged.dat". Download archive VEX_GED_Markus.zip from the link above, unpack archive to any folder and run Setup.exe. It will install the voice "Markus". Download and install Java 32-bit if it is not already installed. To check if you have Java, open CMD and type in "java -version". Download archive VEStudio.zip and unpack it to any folder. Inside unpacked folder open "studio" folder and run "VocalizerExpressiveStudio.exe". After launching Studio go to the tab "TTS" and click button "Setup". Select folder "C:\Program Files (x86)\VEX". It's location, where Vocalizer 5.2.3 installed. Next, you'll be asked to select language and voice:
Voice Setup
Click OK. After selecting language and voice the tab "TTS" will look like this:
TTS Setup
Now go to the tab "User Dictionary Editor" and press "New" button in upper-right corner. Click "Add" button to add new words. Inside textbox "Sounds Like:" enter text - modified pronunciation. Click button "Generate Transcription". It will produce phonetics in L&H+ format. Click button "Copy To Dictionary Entry":
Add words to dictionary
After dictionary is full, press "Save" button in upper-right corner:
Save dictionary
Select option to save dictionary as binary DCB file. Rename DCB file into "userdct_ged.dat" (also change extension).

Now, we have the file "userdct_xxx.dat", created by Python or by Studio. It's time to install this dictionary. Installation is just copying this file into the "components" folder of the installed Voice. For example, in case of Finnish voice, copy "userdct_fif.dat" to the C:\Program Files\VE\languages\fif\speech\components. In case of German voice, copy "userdct_ged.dat" to the C:\Program Files\VE\languages\ged\speech\components. Now, if you open TTS application, the pronunciation of words, defined in dictionary will change.

The file userdct_fif.dat is a language specific dictionary – it can be used by either voice of the same language. If you want it to be used only by particular voice, such as Satu, you must rename it (or create new) to userdct_fif_satu.dat.
For the particular voice you can also add another dictionaries – these must be referenced in *.HDR file of the Voice. If you've created new dictionary named userdct_fif_satu1.dat, then you must add the following code to the end of *.HDR file:
<RESOURCE content-type="application/edct-bin-dictionary;loader=broker">
  userdct/fif/satu1
</RESOURCE>

Here, the slash corresponds to the underscore in the filename. So, the end of *.HDR should look like this:
<RESOURCES>
<!-- The next entries specify default broker strings for the user dictionary resources, once language specific and once voice specific -->
<RESOURCE content-type="application/edct-bin-dictionary;loader=broker">
  userdct/fif
</RESOURCE>
<RESOURCE content-type="application/edct-bin-dictionary;loader=broker">
  userdct/fif/satu
</RESOURCE>
<RESOURCE content-type="application/edct-bin-dictionary;loader=broker">
  userdct/fif/satu1
</RESOURCE>
<!-- The next entries specify default broker strings tuning resources if available -->
</RESOURCES>

All user dictionaries must be located inside "components" folder of the Voice/Language.

Vocalizer Expressive 5.2.3 (Previous Release)
Here are 87 voices from previous version of Vocalizer - Vocalizer 5.2.3. All these voices, including Sin-Ji, Mei-Jia and Tian-Tian have the Premium High quality and can be installed on Windows XP. However, this release is not compatible with Vocalizer 5.4. Therefore, before installing Vocalizer 5.2.3, the Vocalizer 5.4 must be uninstalled if it exist. Similarly, before installing Vocalizer 5.4, the Vocalizer 5.2.3 must be uninstalled.

American English - Allison, Ava, Samantha, Susan, Tom
Arabic - Laila, Tarik
Argentinian Spanish - Diego
Australian English - Karen, Lee
Basque - Miren
Belgian Dutch - Ellen
Brazilian Portuguese - Felipe, Luciana
British English - Daniel, Kate, Oliver, Serena
Bulgarian - Daria
Canadian French - Amelie, Chantal, Nicolas
Catalan - Jordi, Montserrat
Chinese Mandarin - Tian-Tian
Colombian Spanish - Carlos, Soledad
Czech - Iveta, Zuzana
Danish - Magnus, Sara
Dutch - Claire, Xander
Finnish - Onni, Satu
French - Audrey, Aurelie, Thomas
Galician - Carmela
German - Anna, Markus, Petra, Yannick
Greek - Melina, Nikos
Hebrew - Carmit
Hindi - Lekha
Hong Kong Cantonese - Sin-Ji
Hungarian - Mariska
Indian English - Veena
Indonesian - Damayanti
Irish English - Moira
Italian - Alice, Federica, Luca, Paola
Japanese - Kyoko, Otoya
Korean - Sora
Mexican Spanish - Angelica, Juan, Paulina
Norwegian - Henrik, Nora
Polish - Ewa, Krzysztof, Zosia
Portuguese - Catarina, Joana, Joaquim
Romanian - Ioana
Russian - Katya, Milena, Yuri
Scottish English - Fiona
Slovak - Laura
South African English - Tessa
Spanish - Jorge, Monica
Swedish - Alva, Klara, Oskar
Taiwanese Mandarin - Mei-Jia
Thai - Kanya
Turkish - Cem, Yelda
Valencian - Empar


Claude v1.0
Warning: some Characters contain nudity
Supported OS: Windows Xp - Windows 11 64bit
Other requirements: None
Installation: run ClaudeInstaller.exe as Administrator
Description: Claude is Text-To-Speech program with built-in support of MSAgent and SSML 1.0. The interface is intuitive and simple. It doesn't have many settings because its purpose is a preservation of MS Agent technology which is only present in older OS'es preceding Windows 7. Claude automatically fixes the absence of MSAgent in recent versions of Windows and puts 40 Characters to their default location.
This program can open, edit and speak the following formats: HTML, RTF, DOC, DOCX, TXT, XML. It can operate in two modes - with MSAgent enabled or disabled.
To switch into second mode uncheck "Use MSAgent".
To install your own MSAgent Characters copy *.acs files to folder "C:\Windows\MSAgent\chars".
Additional notes: HTML files, containing Unicode, must have tag <meta http-equiv="content-type" content="text/html; charset=UTF-8"> inside their <head> tag in order to correctly render in Claude.
Screenshots:

With MSAgent Without MSAgent SSML

Download: ClaudeInstaller.exe 125Mb (MD5: 963ff3692804ceb0cb155ce8c49fbe36)

240 comments:

  1. This comment has been removed by the author.

    ReplyDelete
  2. Thank you very much friend.
    This is a great post indeed :)

    ReplyDelete
  3. I was just looking on the net
    because I have the same voices
    on Android and are amazing.
    Great Job.
    you are a Genius :)

    ReplyDelete
  4. This comment has been removed by the author.

    ReplyDelete
  5. Hello. Is there any possibility to make SAPI5 version of the new VE 2.2 voices?

    ReplyDelete
    Replies
    1. Hi. Yes, it is possible. But these VE 2.2 voices would be incompatible with 5.2.3 version, because they use single database file instead of several.
      I can make SAPI-5 version of those voices and put them to separate folder on a server. However, VE 5.2.3 must be uninstalled before using them.
      So, which voice are you interested in?


      By the way, VE 2.2 for NVDA is not exactly "new". It still belongs to V5 line of products. Their quality is almost same as VE 5.2.3. The newest version is Vocalizer 6 (Enterprise), which has quality much better than V5. You can check it on example page https://www.nuance.com/landing-pages/playground/Vocalizer_Demo2/vocalizer_modal.html?demo=true
      Unfortunately, there is no download links on internet for Vocalizer 6. V6 must be bought directly from Nuance.

      Delete
    2. I would be interested in the new VE 2.2 Finnish voices. Can you upload them please?

      Delete
    3. I've uploaded them here. Vocalizer 5.4 is exactly the same as VE 2.2 (2.2 is a numeration, used by NVDA only). The links for the Finnish voices Onni and Satu would be https://userscloud.com/p382cd1fts64 and https://userscloud.com/rvp6jynhdo34

      Delete
    4. Thanks. Sorry, I didn't know VE 2.2 is only a numbering used for NVDA. Thought it was a completely new version.

      Delete
  6. 2017.10.17 – I've updated Vocalizer to version 5.4. It includes some new voices such as Telugu Geeta.

    ReplyDelete
  7. Are there any tools to modify the pronunciation data for these Vocalizer voices?

    ReplyDelete
    Replies
    1. I can think of only one tool, called "Vocalizer Studio". It is supposed to be able to edit user dictionary files. It's fully commercial product and I didn't find any cracked version of it. So, I would advise to forget about it. Instead, I've added a little guide to the end of post on how to edit pronunciation.

      Delete
    2. Thanks a lot for the guide, I really appreciate it.

      Delete
  8. This comment has been removed by the author.

    ReplyDelete
  9. Hola de nuevo. ¿Sería posible que me envíes un correo electrónico a vlajna95 at gmail dot com?
    Para mí es muy importante contactarte...

    ReplyDelete
  10. sir i have one query about voices, some file does not have any extension like ( hindi voice neel) so those file cant open in my computer and another file easily open with win rar . pls solve this issue as soon as possible thank you

    ReplyDelete
    Replies
    1. *zip.001,*zip.002 are extensions of split archive. These files must be put together in the same folder. Then you can open *zip.001 with 7-Zip or WinRar and extract.

      Delete
  11. can it be used in youtube videos for commercial purposes? is that has a copyright?

    ReplyDelete
    Replies
    1. Since Nuance doesn't have the official version of the Vocalizer Expressive for Windows, this software doesn't have any licence associated with it. Therefore, you can use "Nuance Vocalizer Expressive TTS 5.4" for any purposes without restrictions.

      Delete
  12. Would it be possible somehow to get the older Acapela Infovox Desktop 2.220 TTS package to work as a SAPI 5 synth under Windows 10? Or, if that's not possible, is there a newer SAPI 5 version available somewhere?

    ReplyDelete
    Replies
    1. If you're going to use Acapela 2.220 on Win10 you'll need to replace the file acattssapi5.dll with newer version from later releases (infovox3 or infovox4). Here is a magnet link:
      magnet:?xt=urn:btih:76D08C69607755279772C2AC0680FF36A1EBACB2&tr=http%3A%2F%2Fbt2.t-ru.org%2Fann%3Fmagnet&dn=Acapela%20Alyona%3A%20MS-Sapi%205.1%20layer%20%D0%B4%D0%BB%D1%8F%20windows%208%20%D0%B8%208.1%20%D0%B8%2010%3A%208%2C0%2030008%2C1%20%5B2011%5D

      Infovox4 works in "demo" mode – it has three restrictions:
      1. Works only 1 hour after PC startup. After 1 hour you'll need to reboot
      2. Speak only 1 sentence at time. If encounters "Dot" it produces beep
      3. The sentence length must not exceed 987 symbols
      If you're familiar with C# or VB.net or even C++, you can write your own TTS application to bypass restrictions 2 and 3. The "1 hour" thing can be solved by using TimeStopper.

      Delete
  13. Unfortunately that magnet link appears to be incorrect. I tried to download it using uTorrent, but it said something about not being able to parse the link.

    ReplyDelete
    Replies
    1. Strange... "Deluge" downloads this link correctly. Anyway, here is the webpage with that link:
      https://rutracker.org/forum/viewtopic.php?t=4424790
      You can get *.torrent file there if the magnet doesn't work

      Delete
  14. The magnet link from that page worked. Thanks.

    ReplyDelete
  15. are those voices full version? or trial version?

    ReplyDelete
  16. Hello my friend, i have a question, are this software and voices trial or unlimited version ?

    ReplyDelete
  17. Thank you very much, dear sister Lea Walter... may God bless you for providing full versions these standard natural voices. I have been searching for a long time all these full versions :-)

    ReplyDelete
  18. I should inform you that among all the provided download links, Indian Bengali voice Paya's part1 is broken. PLEASE, update it so that I can download it. Thanks.

    ReplyDelete
    Replies
    1. It's not broken. You'll also need to download Part2, put two files in the same folder and open Part1 with 7-zip or WinRar

      Delete
  19. You have not understood my comments... I know very well how to combine various parts into one with HJSplit. I already downloaded Part 2 without any issue, however whenever I click on Part 1 download link on Userscloud it shows this error page...
    "This site can’t be reached
    The webpage at https://d8.usercdn.com/d/qqly4chbtv2fvxijh3ayzbcakmmggwn5lfokksmxpeye5nlcu6r3eehsnplc3ktmt3342eqw/VE_Indian_Bengali_Paya_22kHz.zip.001 might be temporarily down or it may have moved permanently to a new web address.
    ERR_INVALID_RESPONSE"

    Wish I could share you the exact screenshot :-(

    I downloaded other 4 Voices, but no errors during their downloads,... exceptional to this Part 1 of Paya Bengali voice. Please, provide alternative links if you have to download. Thanks.

    ReplyDelete
    Replies
    1. Indeed, it was an error of Userscloud. I've updated the link. Now it's https://userscloud.com/2hqw04x2s6bh
      If you're unable to download this file, let me know by posting comment here.

      Delete
  20. Yes... It's working now... Thanks a lot :-)

    ReplyDelete
  21. The "American English - Allison" On Win-XP is working fine.
    But "British English - Malcolm" does not work and produces an initialization error. :((

    ReplyDelete
  22. where can I find the list of 3LetterLanguageCode?, I want to know what is my 3LetterLanguageCode

    ReplyDelete
    Replies
    1. It would depend on Voice. You'll need to find out where the Voice is installed. For example, in case of "Francisca", the full path is "C:\Program Files\VE\languages\spl\speech\ve\ve_pipeline_spl_francisca_22_premium-high_1-0-0.hdr"
      3LetterLanguageCode is a child directory of the "languages" directory. In this case it's "spl". Also, 3LetterLanguageCode is contained within the name of HDR file. Here it's shown as "pipeline_spl_francisca". So, 3LetterLanguageCode=spl

      Delete
    2. Thanks for your fast respond. I thought it was not necessary to asked that question since google know a lot of thing, so I did searching for hours but ended up with nothing. Seems like google don't know about 3LetterLanguageCode yet.

      Is there a free/full version software to edit pronunciation through graphical user interface, instead of the way which you have provided up there? I mean software like neospeech's VT-editor, unfortunately it's not free and I have not find the full version of it.

      Delete
    3. "Nuance Vocalizer Studio" has a graphical interface and can edit user dictionaries, but it costs some money... "Chant Developer Workbench 2016" seems to have 30-day trial (you can install it with Revo Uninstaller and reinstall later). This product includes the "LexiconKit" – the tool to create, edit, export, and import lexicon word pronunciations. I did not test it though, and I can't say for sure wheter it will work with VE 5.4

      Delete
  23. what is L&H+ Symbol for "c" as in "charlie"?

    ReplyDelete
    Replies
    1. I don't know. This information is stored inside PDF document, called "RealSpeak Telecom Software Development Kit User's Guide for American English V4.0 2005" and I can't find it anywhere.

      Delete
  24. Lea Walter, thank you very much! Low bow to you! Do they work without time limits?

    ReplyDelete
    Replies
    1. They don't have any time limits or trial periods

      Delete
    2. Thank, thank, thank, Lea!

      Delete
  25. I should inform you that Italian voice Federica's (VE_Italian_Federica_22kHz.zip) is broken. PLEASE, update it so that I can download it. Thanks.

    ReplyDelete
  26. I'm looking for the Cepstral voices (http://www.cepstral.com/en/personal/download/?os=windows&refpage=windows) and Innoetics TTS voices (https://www.innoetics.com/). Are there full versions available somewhere?

    ReplyDelete
    Replies
    1. It seems the last version of Cepstral voices is 6.2.3.801 and there is no keygen for it yet (I don't think the keygen from Black Riders will work). Of course, you can download these voices from official website, install them with Revo Uninstaller and reinstall later when trial period ends.
      Speaking of Innoetics... I'm not sure if these voices are available anymore, because in July 2017 Innoetics was bought by Samsung.

      Delete
  27. i want know, how to enable automatic language switch? i am using Nvda screen reader i want read Arabic and English.

    ReplyDelete
    Replies
    1. It looks like NVDA supports "automatic language switch" only for voices, installed as add-ons. These voices are SAPI5 and therefore, do not support this feature.

      Delete
    2. thanks very much

      Delete
  28. This comment has been removed by the author.

    ReplyDelete
  29. It works well earlier but suddenly i got error today..

    Cannot synthesize the speech
    Class not registered

    Pls help..

    ReplyDelete
    Replies
    1. Could you give some more specifics:
      1. Which version of Windows do you have
      2. What's the name of voice
      3. Which another SAPI5 voices are installed and do they work?

      Delete
  30. Hello Lea I'm Indonesian I Have Done to download "VE_Indonesian_Damayanti_22kHz.zip" I'm using Software of "Balabolka" can you tell me how to Install it? Thanks Lea Walter

    ReplyDelete
    Replies
    1. Yes Lea, I Have same Problem, please Help! Thank you..

      Delete
    2. Extract the file "VE_Indonesian_Damayanti_22kHz.zip" to any folder, run Setup.exe and follow instructions. After installation is complete, you can open Balabolka and select voice "VE_Indonesian_Damayanti_22kHz" on the "SAPI5" tab.

      Delete
    3. This comment has been removed by the author.

      Delete
    4. well I have done all the stages you have given, but I still can not use it, there is a display message like this: "Can not synthesize the speech:
      Class not registered." can you explain to me, what does that mean? Sorry to bother you Lea.. :(

      Delete
    5. This error means "Damayanti" wasn't installed correctly, but that doesn't make sense, because this voice is working fine on my Win10. Have you tried to install any of VE54 voices on a "fresh" operating system? Perhaps, there is some program interfering with Speech API.

      Delete
    6. Hi I can not play the voice in Spanish in balabolka, nor in text to speech, nor in naturalreader. send me a message:

      "Can not synthesize the speech:
      Class not registered."

      I have window 10 single home!
      Thanks
      Voice Juan

      voice the IVONA

      Please help me!!!

      Delete
  31. Hey please upload part 1 of Marathi voice Ananya. It got deleted! I need it. ��

    ReplyDelete
    Replies
    1. I get "The file you are trying to download is no longer available" for it.

      Delete
    2. Part 2 download link is working fine. Part 1 Ananya was deleted by Userscloud. :(

      Delete
    3. https://userscloud.com/ut1dn7owczj1

      Delete
    4. Thank you so much! This helps very much. I am a native Marathi speaker but schooled in English medium so I find it hard to read it fast but I can write and read it slowly, although not at the speed at which I can read English. So, long articles and texts in Marathi take time for me to finish reading. Now with this TTS voice, it will read them out for me faster than I read it.

      Delete
    5. Indian Bengali Voice Paya's part 1 was also deleted by Userscloud. Part 2 is downloadable. Please re-upload. :)

      Delete
    6. https://userscloud.com/0hfp0nmigk8i

      Delete
    7. Thank you Lea. You are very helpful. All my friends from India speaking dozen Indian languages bless you.

      Delete
  32. hi admin thanks
    this voices are very helpful
    i have downloaded INDIAN HINDI LEKHA voice and it is working well
    But INDIAN HINDI NEEL voice does not working.After downloading when i try to extract,it shows a messare that " C:\Users\Abhik\Desktop\VE_Hindi_Neel_22kHz.zip: The archive is either in unknown format or damaged
    C:\Users\Abhik\Desktop\VE_Hindi_Neel_22kHz.zip.001: The archive is corrupt"

    Thanks
    Please update it in a single file.I need it too

    ReplyDelete
    Replies
    1. You need to download the corrupt/half finished archive again. I just downloaded all Hindi and Marathi voices and currently all links are fine and extract perfectly.

      Delete
    2. The file "VE_Hindi_Neel_22kHz.zip.001" is not corrupt - it's part of split archive. To open it correctly with program 7-Zip you'll need another file "VE_Hindi_Neel_22kHz.zip.002" in same folder.

      Delete
    3. thanks admin. you are great
      actually during download i have changed 2nd file name from .zip.002 to .zip ,thatswhy i was unable to extract.now its working fine
      thanks

      Please don't mind, is really these voices are 100% free for lifetime.actually i can't believe.this really great

      Delete
  33. Hello Lea Walter, I realy need help on modify the pronunciation.

    example word: you

    Edit The pronunciation to: yes

    you // #'jEs#

    Let's say, the pronunciation result is exactly as what I want

    but if the word in the text area is something like this:

    "you"

    The TTS App doesn't pronounce it as I want, in other words this string: ( you // #'jEs# ) which I added to the dictionary doesn't work for this: ( "you" )

    So I Add the following string in the dictionary:

    "you" // #'jEs#

    but it doesn't work either.

    How to deal with double quotation marks word?

    ReplyDelete
    Replies
    1. After strugle for months finaly it SOLVED by using backslash (\) before double quote (").

      Example:

      \"you\" // #'jEs#

      Delete
    2. Sorry for late response but I didn't know the answer to your question. The only description I found, is that source string must not exceed 40 characters. By the way, do you have access to L&H+ alphabet for English?

      Delete
    3. You can get it from VoCon's installation directory

      C:\Program Files (x86)\Nuance\vocon3200\EDS_v3_3F1\man\PhonemeTable_enu_400.pdf

      Delete
  34. hi thanks for your voice
    can you please upload more indian hindi voices?

    ReplyDelete
    Replies
    1. Hi. At the present moment there are only two Hindi voices made by Nuance - Lekha and Neel. If in a future Nuance will make another voice, I will try to upload it here.

      Delete
  35. Please Upload Multi Language TTS

    ReplyDelete
    Replies
    1. Hello, this page relates only to standard TTS technology. As far as I know, Multilanguage TTS is in the stage of early development and popular companies like Acapela, NeoSpeech, Nuance didn't make such engine yet.

      Delete
  36. Hi,

    I would like to ask a few questions regarding these voices:

    1. you updated from version 5.2.3 to 5.4 where single file variants of the voices were released.
    I would like to know if the older archive is still available and what version number the ve.dll of v5.2.3 had.
    I have seen older voices with v1.1, v1.3 and also v1.5 but it was always named Vocalizer Expressive and never Vocalizer Embedded.

    2. Was there ever a version 5.3?
    I am asking because for a time Vocalizer for Android from CodeFactory shipped voices where in each file name for downloadable voices they had the v1.5.0 added to their name.
    There was for example a multi file version of Rishi, before you released your new single file variant of voices.
    These voices also existed for Windows before they got updated. There the ve.dll was V1.5.0 and was named Vocalizer Expressive and was the first variant where end users saw a 32-Bit and 64-Bit DLL if the user had a 64-Bit system.

    3. I know that Vocalizer is supposed to have some multilanguage versions of voices.
    the first Vocalizer Expressive package for the NVDA screen reader had petra-ml and audrey-ml, but the multilanguage features were never usable probably due to a custom made interface.
    But the voices and the language files were different compared to the standard versions of these voices.
    For example 5.2.3 Petra was around 138 MB (premium high) while petra-ml had 222 MB in the same quality.
    The current voice packages still should contain ml variants of some voices and not only in Vocalizer 6.

    4. Is there a single file version of the Siri voices so that they might be included in this package?
    Some years ago some Siri voices were published and it was known that these were compatible with Vocalizer 5.2.3.
    But no one seems to have seen a V5.4 compatible version of any of them.


    5. CodeFactory released an updated version of Vocalizer voices.
    They went from Vocalizer Expressive 2.1.0 or 2.2.0 (which compares to your voices) to Vocalizer Embedded 3.2.
    They released new files, brought in a new US English voice called Noelle and it also looks like as if the new package does not contain any premium high variants of anything.

    Moreover Harpo seems to have updated their voices as well, even single file voices like Anna got reduced in size from 590 MB to 194 MB (for trial versions at least) and they are selling Noelle now, allthough you have to search her on the harpo site.



    6. Can you get other voice variants like embedded-compact or the other variants in the middle quality range?
    I am asking for comparison purposes and because I don't get why some asian voices should not exist in high quality.
    They did in V5.2.3, if I remember right. And it seems unlikely that they updated voices to make them better and then dropped quality down to a fraction of their original state in the switch to v5.4.

    ReplyDelete
    Replies
    1. Hi, I'll try to answer your questions
      1. The version of ve.dll of v5.2.3 is 1.3.0.13329 and VE v5.2.3 is no longer available, because I made some mistakes in that version.
      2. I have no idea if ever was a version "5.3". There are many distributors of the same product "Vocalizer Expressive". Examples of distributors: Ai Squared, GW Micro, kobaspeech.com, harposoftware.com, Freedom Scientific... Some of these have their own naming for the version of voices. I took "5.4" from XML file, describing the voice.
      3. It seems the "Multilanguage voices" are present only in Vocalizer 6. I didn't find any "-ml" voices for Vocalizer Expressive. If you find such voice, let me know.
      4. Siri is a "Virtual Assistant" in iOS and macOS, right? I don't think the voices from this release can be installed on Mac and vice verse.
      5. I'll try to make Noelle and Joelle as soon as possible. Another voices such as Malay Amira will have to wait until they spread in Internet enough.
      6. I don't plan to include "compact" voices, since it does not have a sense. "compact" variants were developed when home computers had minimal resources. Now, even low-end laptop has at least 4 Gb of memory. And I agree with you that Asian voices must also have premium-high quality. Unfortunately, the new version of ve.dll is incompatible with older 5.2.3 voices.

      Delete
  37. Update 2018.05.28: Added two US English child voices Joelle and Noelle

    ReplyDelete
  38. Hello when i am trying to install this its given error Your system has not been modified. To complete installation at another time, please run setup again please update me thanks

    ReplyDelete
    Replies
    1. Hello, could you specify the following:
      1. What's the name of Voice
      2. What's Operating System version
      3. Have you tried to disable any Antiviruses during installation

      Delete
    2. i am using window 10 and voice is Neel (Indian)

      Delete
    3. I've checked installer on my PC and it runs as expected. I would advise you to disable all antiviruses and run Setup.exe as Administrator. If it will not work, then try to install one of Chinese voices - they have small size. If you'll install Chinese voice successfully, tell me the Path you selected, when installing Vocalizer. For example, C:\Program Files\VE
      By the way, is your Windows 64 bit?

      Delete
    4. Installing path is c , program files speech 2 go folder

      Delete
    5. It explains everything… If you read this website carefully, it says Vocalizer isn't compatible with harposoftware.com. You must uninstall Speech2Go completely, reboot and then try to install Neel again.

      Delete
    6. i am checking on other computer korean voice installed easily but neel voice given error , Nuance 5.4 hindi neel setup ended prematurely because of an error , your system has not been modifired... :/

      Delete
    7. chinese voice also working

      Delete
    8. In that case I can't say what problem is. I tried to run installer on another PC and all work without issues. However, you can install Neel manually. To give you further instructions I need the following information:
      1. What is your Windows version, 64 bit or 32 bit - it's important.
      2. What is Path, where you've installed another Vocalizer 5.4 voice? Please, tell me full path with slashes, like "C:\Program Files\VE"

      Delete
    9. window 7 , 32 bit , location C:\Program Files\VE

      Delete
    10. If your system is really Windows 7 x86 (32 bit), then you'll need to perform these actions:
      1. Extract archive VE_Hindi_Neel_22kHz.zip to some folder. If you already did this, repeat this step again
      2. Navigate into "extracted folder" → "msi". Inside the "msi" directory would be folder "languages". Copy this folder "languages" into "C:\Program Files\VE" directory and overwrite everything.
      3. Download Registry file here https://drive.google.com/uc?id=1tFFaALiCM5UcR_Tfx-GE6acm_fzxpVTZ&export=download
      4. Double click downloaded file VE_Hindi_Neel_22kHz.reg
      5. Click Yes when prompt popups
      6. What's all. Now, if you open Balabolka you should see Neel among other Sapi5 voices.

      Delete
    11. Inside the "msi" directory there is folder "languages" comman folder is empty and hi folder have some folders but no file

      Delete
    12. Probably, you opened "msi" inside older directory, from which you tried to install Neel for the first time. You'll need to delete that old directory and extract VE_Hindi_Neel_22kHz.zip again. The size of "languages" folder must be 933 Mb.

      Delete
    13. its working on window 7 , 32 bit , but the same mehtode i do in window 10 64 bit its not working any other solution for 64 bit?

      Delete
    14. thanks its working on both now , thank you so much :)...

      Delete
    15. You're welcome. To use manual method in Windows x64 you'll need another Registry file https://drive.google.com/uc?id=1mrEXDxXRgoFBTZqKLXqKUMTipgZPIcHI&export=download

      Delete
  39. could you , please , upload Otoya tts again? it can't be installed !

    ReplyDelete
    Replies
    1. https://drive.google.com/uc?id=1p4CZMg4baM_2KTWQkx2u-qa3_tFRBEex&export=download

      Delete
  40. This comment has been removed by the author.

    ReplyDelete
  41. Thank you , Lea , now it's working fine . You have the best collection of voices in the web . Congratulations for your useful work . God bless you . thank you , very much.

    ReplyDelete
  42. Thank you Lea Walter, Thank you very much.

    Please try to add (Raveena - Indian English voice, woman) here in your collection.

    Have a great life ahead...

    ReplyDelete
    Replies
    1. Sorry, but I don't know how. This is not Nuance, but Ivona voice.

      Delete
  43. Lea are you really the person behind all of this, who made all of these voices became full? Are you the first person who release these full version voices? Are you a programmer who can do whatever you want? If so then could you update the indonesian voice please, because it still has many incorrect pronunciation, absolutely a lot. Thanks

    ReplyDelete
    Replies
    1. I'm not a person, who made all these voices. I only made Sapi5 version of them. If I remember correctly, Damayanti was created by Nuance (It's not original Loquendo voice). From what you said, Damayanti needs a full-scale user dictionary. On this website I already described this technique. To make such dictionary programmatically you'll need usual Indonesian phonetic dictionary, where each word has its phonetic representation in IPA (International Phonetic Alphabet). Since I don't know this language, I have no idea where to seek such dictionary. It must exist on some Indonesian linguistic websites.

      Delete
  44. thanks very much, i am from indonesia, i download damayanti vocalizer.

    ReplyDelete
  45. Thank you! Your work is very appreciated.

    ReplyDelete
  46. Thank you very much, It saved lot of money and time... :) _/\_

    ReplyDelete
  47. Lea, Colombian Spanish does not open in Windows XP. Popping up windows with errors.
    Can you help me make some adjustments?

    Generally with Nuance voices some problems are constantly on Windows XP. Then work, then do not work immediately after installation. There's no such thing with Ivona voices. They work fine. :(((

    ReplyDelete
  48. Lea, to the previous comment:
    -it turns out that if Win XP installed first VE-voice Speech2Go, after it has been installed your Installer starts to be installed in the directory "Speech2Go Voice Package VE " and starts and runs normally!

    Some interesting glitch)))

    But some voices even in this case, don't work on Win XP.
    E.g. Malcolm voice. And after their installation, all VE-voices cease to run.

    How does it solve?
    Do they only work reliably on Win7 ??

    ReplyDelete
    Replies
    1. All voices should work fine on Windows 7/8/10. Unfortunately, these voices
      Alpana, Ananya, Angelica, Federica, Fernanda, Francisca, Geeta, Jaya, Joelle, Kanya, Lana, Malcolm, Noelle, Paya, Sangeeta, Vani, Viktor
      will not work on Windows XP, because they have different registry settings or may be, they require SAPI version 5.3, while XP has SAPI version 5.1.

      Delete
  49. Hello, could you make Croatian Lana Voice, in embedded-pro quality, because its somehow sounds better than high premium. Thanks.

    ReplyDelete
    Replies
    1. Hi, I can only make voices from existing products. Could you please clarify which product do you mean when you said "embedded-pro" quality.

      Delete
    2. Code factory have now sapi5 voices, which are embeded pro quality, about 110 mb per voice.

      Delete
    3. I tried to make the voice but without success... The files "ve_pipeline_hrh_lana_22_embedded-pro_1-0-4.hdr" and "hrh_lana_embedded-pro_1-0-4.dat" are encrypted. The .hdr, instead of being plain XML, begins with "vG?.P<]#\,4hdzBborFbo7..."
      So, when I made the voice, I got an error "Can not synthesize speech". Obviously, to make working solution I need an unencrypted voice data. If you find it somewhere let me know.

      Delete
  50. I would like to download VE_Hong_Kong_Cantonese_Sin-Ji_22kHz PremiumHigh voice. Can you tell me where I can download it?

    ReplyDelete
  51. please help me with Cantonese Sin-ji PremiumHigh Voice, I really need this voice. Thank you!

    ReplyDelete
    Replies
    1. I've decided to remake previous version of VE. Version 5.2.3 would include Asian Premium High voices and would have support for Windows XP. When I finish the job, I'll post comment here.

      Delete
  52. This comment has been removed by the author.

    ReplyDelete
  53. Hello Lea, i really need voices from acapela group (laura,rod,saul,will,peter etc). Have been search many hours on internet, but nothing i found.
    highly appreciate if you could help us. thank you.

    ReplyDelete
    Replies
    1. Unfortunately, Crack for infovox4 does not exist yet, but you could download older version of Acapela v2.2, released in 2008.
      Here is link to webpage with torrent:
      https://rutracker.org/forum/viewtopic.php?t=1366333
      You'll also need another file from here https://rutracker.org/forum/viewtopic.php?t=4424790
      in order for Acapela to work on Windows 8/10.

      Delete
    2. oh my god, released in 10 years ago. but not bad to try it out. thank you Lea. You are awesome.

      Delete
    3. btw, i am so amazed with SSML voice editor of IBM watson. many features of expression like "express as apology, goodNews, etc.
      yea i know i can use xml tag on balabolka - for example - but it's not good as IBM has.

      have you take a look here?
      https://text-to-speech-demo.ng.bluemix.net/ and here: https://ivva-tts.sl.haifa.il.ibm.com/design

      unfortunately, Their web response is too slow for me. so it's boring. I didn't know why.

      seems like there is no alternative / similar to that.
      do you have any idea?

      Delete
    4. I'm not aware of a TTS program like Balabolka with SSML support. However, Microsoft .Net class SpVoice has support for SSML. Usage Example in VB.Net:
      Dim sp1 As New SpVoice
      sp1.Speak("Some text", SpeechVoiceSpeakFlags.SVSFParseSsml)
      Besides, it's not clear if all IBM "expressive" tags are supported by SpVoice.

      Delete
    5. Nice idea. I am not familiar with Microsoft VB Net, i am just using Embarcadero as my main language for daily usage.
      but i'll try to do my best.
      again, thank you Lea. You helped us alot. GBU

      Delete
  54. thanks...any child or baby voice are there..please inform.

    ReplyDelete
  55. Greetings Lee,
    Thanks a million for all your hard work; it truly has made a tremendous impact in my life in many ways--too many to list--. Please see below for a few important questions.

    First, I've just found out from Codefactory website that there are apparently cool new voices in the latest iteration of Vocalizer like Korean Nuri and UK English Stephanie; is there any way you can also make these voices available as soon as possible? Especially being Korean, Nuri sounds far more natural compared to existing voices from Nuance; since you have been able to make Joelle and Noelle available, I'm very curious.

    Second, would you be able to bring Vocalizer 6 anytime soon? I particularly like new voices in that version like Evelyn and Evan for American English; please advise.

    Last but not least, I have read that you are working on bringing the older version back; any further update on that?

    I am greatly looking forward to your detailed reply at your earliest convenience; much appreciated once again Lee. Hope you are having a good weekend!

    Warmest Regards,
    SJ

    ReplyDelete
    Replies
    1. Hi, I'll try to answer your questions.
      1. I know that Codefactory has released some new voices. These voices available for Windows and Android are encrypted. I was able to make Joelle and Noelle because I found their unencrypted version on harposoftware.com. But don't worry, soon or later these voices would be available for NVDA or for some another open source project and then it would be possible to make SAPI5 version of them.
      2. Truth be told, I'm not sure if Vocalizer 6 (Now it's Vocalizer 7 or Vocalizer for Enterprise) would ever be available for individuals. I think Nuance sells this product only to organizations for intended use in Call-centers, banks, etc. I'm certain Vocalizer 6 existed at least four years and during these years I didn't find single mention of its Windows Desktop version.
      3. I'm still working on remaking previous version of VE.

      Delete
  56. I have natural reader 15 and textaloud 4 and use these programs to play stories to my son before bedtime.
    I have been hunting for long time for the acapella child voices of australian girl olivia and english girl rosie. These are so perfect for reading stories to a child.
    I found a 15 day acapela trial you can download and use with NVDA but then after you need to pay license to continue. I will continue my hobby of hunting for a torrent for child voices for nextup or natural reader.
    Curiosity has made me post here after seeing how much you communicate with people and really try to help them. This impressed me as its pretty rare to see these days.

    Anyway, I just wanted to say hello.

    ReplyDelete
  57. Ok so im back ( i read to my son post )
    Just for kicks i downloaded a voice and it showed up in natural reader 15 and also text aloud 3 and 4.
    Was not expecting to see that........so i downloaded a few more and they all work....kool.
    Lea thanks for sharing these voices, now i have more adult variety other than microsoft sam :)
    The Joelle and Noelle child voices are not too bad but i am still hunting for Olivia and Rosie.
    I shall not give up ")

    Ok now i put name to my post = thanks GT

    ReplyDelete
  58. i am using natural reader 14 ...but i can't use pause in conversational control...please suggest me how i do it.

    ReplyDelete
    Replies
    1. Do you mean you can't find "Pause"? When you press ▶️ button it will change into ⏸️ button.

      Delete
    2. Many many thanks for your response LEA WALTER....no i want to know how to set 5 second or 10 second break after a sentence...

      Delete
    3. Try to insert into NaturalReader text like this:
      NaturalReader is a professional text to speech program that converts any written <set xml=true><silence msec="9000"/> text into spoken words.

      Delete
    4. yeah... i had already done...but it not worked..
      thanks

      Delete
    5. dear sister lea...please upload some other bengali and hindi voice if possible...thanks..

      Delete
    6. All Hindi voices, made by Nuance are present here. If you want something new, try to use the internet search. I'm only aware of the "Google Text-to-Speech" app, which includes Hindi and Bengali voices. To use them on Windows install Memu Play, inside Memu go to settings, languages and input, text to speech and select Google TTS as default engine. In Google TTS settings, download necessary voice data.

      Delete
    7. THANKS FOR YOUR GREAT IDEA.... I WILL TRY...

      Delete
  59. I want to use it in balabolka, sapi 5, but the Spanish voice of JUAN does not work, what do I do? Thanks Thank you for your hard work, I appreciate it very much.

    ReplyDelete
    Replies
    1. Do you mean VE_Mexican_Spanish_Juan_22kHz voice, which you downloaded from here? It should work. If it's not working, then may be several reasons. Most probably, you have the corrupt SAPI5 settings on your PC.
      Try to answer these questions:
      1. What another voices you've installed besides Juan? Give complete list as shown in Balabolka
      2. Do another voices work?

      Delete
  60. Hi admin Thank you thank you very much ....I m very grateful to you.....thank you thank you thank you

    ReplyDelete
  61. Update 2018.09.20: Added Vocalizer 5.2.3. I would not recommend this version unless you have Windows XP or you specifically need Asian voices Sin-Ji, Mei-Jia and Tian-Tian.

    ReplyDelete
  62. Hello Lea am back , you really did Nice Work do you have URDU TTS? i really need it..

    ReplyDelete
    Replies
    1. Nuance doesn't have Urdu voice yet

      Delete
    2. Lea..!!!!
      I really like this picture on this page.
      Its so green, I love it and i want it.
      Please can you tell me where you got it.
      Its beautiful country side.
      Thanks
      GT

      Delete
    3. It's part of theme, provided by blogspot.com
      Here's direct link
      http://themes.googleusercontent.com/image?id=1M-C2rHwLzLDZGoh3qbWZ6sde9R5UC4jZcYt-QoyO1RyATwD6rQGlARx_UmuMWy_AlUTn&options=w1600

      Delete
    4. sweet!
      Many thanks
      GT

      Delete
  63. hello bro, thanks a lot of those voices i'd like to ask if you could give me ATT voices and accapella infovox 4 if there is any crack, i tryed to search but couldn't find anything

    ReplyDelete
    Replies
    1. You can download AT&T voices by using Torrent-Client. Here is link to torrent file:
      https://www.seedpeer.me/torrent/9f8b02c8c00135bb53a60d96222043536a33e878

      As far as I know there is no keygen/crack for Acapela Infovox 4

      Delete
  64. ah, i had tryed this link before, but i saw it just stoping in 0.54 % , then nothing happeneds, i retryed a lot of times, but seames my torrent programe is not responding, or the link is broking, do you have any other links, like drop box or google drive, i have enough space my db if you have one or something elss, thanks again

    ReplyDelete
  65. i dont know how to thank you, you've saved my life, there is no way to support arabic speech without VE

    please accept my thanks

    ReplyDelete
  66. Wow thx guy, u are best, please accept my thanks

    ReplyDelete
  67. This is a NVDA user commenting here.
    Sadly, Japanese voices don't play katakana syllables except the prolonged sound mark "ー" (chouon) when I press the l/r arrows to read them. But when I write a katakana word and I press down/up arrow, the voice reads the word.

    ReplyDelete
  68. Update 2018.11.16: Added free TTS program Claude with MSAgent and SSML support.

    ReplyDelete
  69. hello, i've recently installed win10 pro, i got this error message setup ended permaturely, because of an erro. your system has not been modified. >>>etc

    How can override this?

    ReplyDelete
    Replies
    1. Which voice you're trying to install and is your Windows 64bit or 32bit?

      Delete
    2. I would to thank you for replay, but i found a serious problem in an installation of the voice pack Laila Arabic voice v 5.4,
      i downloaded the pack from couple months ago, and installed it successfully but when tried to install the old unpacked files on windows 10 pro x64, the error message appeared.

      re downloading zipped pack, unzip, compare folder's files !!! wow they differ ?
      I think after the installation the installer delete some files !! Am i right?

      I hope this help some people

      Thanks again

      Delete
    3. This is usual behavior of Windows Installer. After installation is complete, Windows Installer will delete files in unpacked folder because it assumes them been temporary.
      Have you installed re-downloaded package successfully?

      Delete
  70. I just wanted to thank you for 'Claude' it has enabled me to still use the Office Assistant in Windows 10, I've missed this & appreciate it :)

    ReplyDelete
  71. Thanks foi it ... and keep on ... :)

    ReplyDelete
  72. I just want to tell you that I love your work and I am very grateful. Can you convert the voice of Rodrigo from acapela group (Mexican Spanish, USA) into sapi5? Thanks!

    ReplyDelete
    Replies
    1. Acapela voices need keygen/crack to unlock them. The closest thing would be installing Acapela for NVDA with RevoUninstaller and then re-installing again when 15-day trial period expires.

      Delete
  73. A million thank-yous for sharing it with the world.

    ReplyDelete
  74. hello, is it possible to download all the voices at once? or to get a link to the folder? lets say on yandex or whatever.

    ReplyDelete
    Replies
    1. Here are two folders:
      https://drive.google.com/drive/folders/1oC4-yOdNBT6jtq8ib5KuQcOXUJ4YensE
      https://drive.google.com/drive/folders/1DPTS42O0IrLvYq2FKsSS0UCwp4lBsXOZ
      Click on the link "Download All"

      Delete
    2. all the voices given on above link are trial versions or full fledged & does not expires?

      Delete
    3. They're not trial and don't need registration

      Delete
    4. ok, btw i am getting synthesis error, can you help me in this?

      Delete
    5. ok, btw i am getting synthesis error with MARATHI ANANYA VOICE, can you help me in this?

      Delete
    6. There are many reasons why this error could appear. I can only guess. Can you answer these questions:
      1. Which version of Windows do you have
      2. Which another SAPI5 voices are installed and do they work?
      3. Did you install anything from harposoftware?

      Delete
    7. 1. windows 7 home premium.
      2. i have ivona voices installed , which works fine. another sapi5 downloaded from your collection were AE NATHAN & SUSAN & works fine.
      3. nothing installed from harpo as they were offering trial & i got all listed in your collection without any trial limit as you answered yesterday.

      Delete
    8. Sorry, but in that case I can't say what problem is. I installed Ananya voice on my PC (win 10 x64) and it works fine. I also have some Ivona together with another VE54 voices installed and they all work.

      Delete
  75. I think the problem could be the reader then, as I used speech2go.
    Which reader doftwaso you were using?
    Which you would suggest?

    ReplyDelete
  76. Also tell one more thing.
    Does both the Google drive links consist same voices or all are different as there are various folder for same voice category for example American English.

    ReplyDelete
    Replies
    1. I would suggest any reader, described in section "Free software to read text aloud". However, I wouldn't recommend "TextAloud 4", because it changes the voices somehow and doesn't support Unicode.

      Both folders contain different voices without any sorting. I published these folders only for convenience, for those who want to download all voices at once. If you want specific voice, you'd better go for download links at the beginning of this page (YandexDisk and GoogleDrive).

      Delete
    2. dear lea, actually the error i am having with these voices is OLE "error 80045012" because of this error i am able to install & use only one voice at a time, if i installs another & use that the previously installed voice shows above error when i try to reuse it :( any solution?

      Delete
    3. This is very strange behavior, I've never encountered it before. Try to reproduce this error in virtual machine: install Win7 from official ISO file and then inside Win7 install few VE54 voices. If this error will not appear it would mean you have corrupt Sapi5 settings on your PC.

      Delete
    4. everything solved now, all working smooth in TA's latest released version.
      just one more question

      AT&T Natural Voices
      Acapela Voices
      Ivona Voices
      Nuance Voices..(have you uploaded everything of nuance?)
      NextUp Talker

      Delete
  77. I mean any possibility of getting all these too?

    ReplyDelete
    Replies
    1. AT&T Voices are 10 years old, but you can still download them using Torrent Client:
      magnet:?xt=urn:btih:9f8b02c8c00135bb53a60d96222043536a33e878&dn=NextUp+-+Text+Aloud+%2B+AT%26T+Natural+Voices+%2B+NeoSpeech+Voices+%2B+SERIAL

      Acapela voices need keygen/crack to unlock them. The closest thing would be installing Acapela for NVDA with RevoUninstaller and then re-installing again when 15-day trial period expires.

      Ivona Voices must be used together with Speech2Go in order to unlock them. Install voices, Speech2Go, then run Speech2GoPNKeygen.exe and generate key for voices. When you open Speech2Go enter key.
      magnet:?xt=urn:btih:eb41ea2e4f45f676dfe5a4b4aa02f3d510ae6235&tr=http%3A%2F%2Fbt02.nnm-club.cc%3A2710%2F00981ab901a53f6ac8417ffcef979e1c%2Fannounce&tr=http%3A%2F%2F%5B2001%3A470%3A25%3A482%3A%3A2%5D%3A2710%2F00981ab901a53f6ac8417ffcef979e1c%2Fannounce

      NextUp Talker is a 30-day shareware. You can use RevoUninstaller in same manner as for Acapela voices.

      Delete
    2. the links you have given, i am unable to access. dont know the problem, is it possible for you to upload them on your gdrive give me link? i would really appreciate that. torrent might be blocked in my country, i think.

      Delete
    3. Sorry, but my google drive is already full. The magnet links are working and have enough seeders. Probably, your Firewall is blocking ports of Torrent-client. So, you'll need to temporarily disable it.

      Anyway, here is Speech2GoPNKeygen.exe (https://docs.google.com/uc?id=1OwB3PWVlzt3JyLheMBBm5EW2YssJ3wYH&export=download). You can download Speech2Go and Ivona Voices from harposoftware.com.

      Just remember, if you use Nuance VE54 from this page, you must NOT download NUANCE Voices from harposoftware.com, because they are incompatible with VE54.

      Delete
  78. Unfortunately no success with magnets :(

    Can you please try uploading Acapela voices on zippyshare?, Please.

    ReplyDelete
    Replies
    1. As I already mentioned, Acapela needs keygen/crack which currently doesn't exist. You can download trial versions from http://www.acapela-nvda.com

      Delete
  79. Dear Lea Walter,
    Thanks to you, I got 'Speech2GoPNKeygen.exe' from Torrent that I can use IVONA VE again. In fact, windows10 build 1511 supports IVONA VE Cracks and I gave up using IVONA VE. However your kindness enabled me to use IVONA VE again. Thanks a million.

    ReplyDelete
  80. Windows10 from build 1607 to 1809 disables users to use IVONA CRACKS... But Speech2GoPNKeygen.exe enables users to keep using IVONA VE...

    ReplyDelete

Note: Only a member of this blog may post a comment.