Microsoft Speech Platform Windows 10

Posted on by

Windows 10 comes with two default voices installed to be used with the text-to-speech engines. These two voices (namely Microsoft Zira and Microsoft David) that come pre-installed in Windows 10 are to be used with both apps and desktop applications. In case you are installing a third party voice pack for TTS then most probably it will be available for the desktop applications only. Here is how you can install third party TTS voices, set them as default and use them in Windows desktop applications:

Download and install TTS Voice Packs in Windows 10

One of the sources for downloading free Microsoft and LTS TTS voices is Zero2000. You can also purchase very high quality TTS voices for Windows from companies like Ivona, Cepstral or CereProc. But if you want to try out these high quality voices in Windows 10, then you can also download the 30-day trial versions too. You can download these various packs from http://visionaid.com/phpincludes/en/support/voices/voices.php where you will find voice packs from Ivona and Nuance (no longer work in Windows 10).

Here, I see that for old Windows version (but not for Windows 10!) is possible to download and install the Runtime and the Package language: Microsoft Speech Platform - Runtime Languages (Version 11). Windows Speech Recognition lets you control your PC by voice alone, without needing a keyboard or mouse. The following tables list commands that you can use with Speech Recognition. If a word or phrase is bold, it's an example. Replace it with similar words to get the result you want. Meet the Speech Platform in Windows 10 Speech Synthesis. The SpeechSynthesis APIs are actually not new. Speech Recognition. The SpeechRecognition APIs are really new to the desktop. Cortana App Invocation. OK, now we are getting somewhere. Cortana Canvas. Finally, (and really the only.

Installation of these packs is usually very simple. All you have to do is launch and go through the setup installer package and it will automatically install all the voices included in the package in your Windows 10 PC.

Testing VisionAid Voices Packs in Windows 10

If you have downloaded the speech packs from VisionAid website (link above), then the setup package installs some extra tools in your PC. You can open the Start Menu icon and search for Speech Test to find a small speech testing tool. The other tool installed is for managing the installed voice licenses on your PC.

The Speech Test tool can be used to check the proper installation of these voices in your PC. You can select one of the installed voices from the drop-down list, then type something in the text box and click on the Speak button. There are some other options for this tool like speak punctuation and parsing XML files.

Setting a Default Voice for TTS in Windows 10

Some voices in Windows 10 are only meant for apps, and some for only desktop applications, while others can be used both for apps and traditional desktop applications. Most of the third party voices are designed to be used with the desktop applications. In order to use them, you have open Control Panel and choose the default voice.

You can press the Win+X and select Control Panel from the menu. In the Control Panel, search for “speech” and then click on the Change text to speech settings. In the window that opens, you can choose a default voice from Voice Selection list-box and then finally click on OK button.

Note: Not all voice packs installed may show up in these settings depending on the API used by them. Even the same voice pack may use different API for different versions of the voice packs. For using them, use specific apps like TTSReader mentioned below.

Using the Newly Installed Voice in Desktop Application

For using the newly installed voices in Windows 10 requires you to either use a Windows app that you can download from the official Microsoft apps store or a desktop application like TTSReader that you can download from http://www.softpedia.com/get/Office-tools/Other-Office-Tools/TTSReader.shtml. Windows 8 free dvd player.

TTSReader is a free application and can read all the text that you have copied to the clipboard automatically. In the application, you can choose one of the available TTS voices and control its speech, volume and pitch. TTSReader can also save the speech output to an MP3 or WAV audio file.

Conclusion: If you are not happy with the default Microsoft Zira and Microsoft David TTS voices available in Windows 10, then you can get third party TTS voices for free or buy them online. Using the third party TTS voices in Windows 10 is a breeze if you know what type of voice packs you have installed.

Related posts:

Microsoft Speech Platform Windows 10

Join GitHub today

GitHub is home to over 40 million developers working together to host and review code, manage projects, and build software together.

Sign up New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Comments

commented Jan 31, 2013

Hi,
I've discovered that the Microsoft Speech Platform (http://www.microsoft.com/en-au/download/details.aspx?id=27225) shares the same COM interface as the Speech API (SAPI) that comes with windows.

I've been able to use the vastly superior Speech Platform voices from here with pyttsx:
http://www.microsoft.com/en-us/download/details.aspx?id=27224

All I had to do was change the SAPI COM object from:
self._tts = win32com.client.Dispatch('SAPI.SPVoice')

to:
self._tts = win32com.client.Dispatch('{d941651c-44e6-4c17-badf-c36826fc3424}')

As far as I can tell there isn't a nice name for the Speech Platform COM object but it does work.

commented Mar 10, 2013

Thanks for the info. I somehow missed this issue when you opened it.

It looks like Speech Platform COM is supported on Windows Vista (and up?) I don't have convenient access to a Windows box to test if all of the functions work at the moment. Could you give the unit tests a run and see if they all pass after your change?

Microsoft

I'm thinking either I can treat the two as separate engines, defaulting to the newest one when available and falling back on SAPI when it's not, but also allow manual override using the API in case someone has SP installed but wants to go back to SAPI.

Microsoft Speech Platform Windows 10
assigned parenteMar 10, 2013

commented Aug 9, 2013

Any chance of giving the unit tests a run to see if things work on Vista and up?

commented Aug 10, 2013

Probably possible. I just need to remember to do it. The project at work I was going to use pyttsx with didn't eventuate. Next time I'm procrastinating I'll see if I can run through the tests on a Windows box.

Open

Microsoft Speech Platform Windows 10 Update

Closed

Microsoft Speech Platform Runtime

commented Oct 12, 2018

Microsoft Speech Platform Runtime 11

I have tried this, it doesn't work.
1 on https://github.com/RapidWareTech/pyttsx/blob/master/pyttsx/drivers/sapi5.py#L56 (in getProperty) it raises
2 if I comment that line out, it is constructed and getProperty('voice') suceeds
3 Cannot start the loop, it hangs, and there is no sound.

Microsoft Speech Platform On Windows 10

Sign up for freeto join this conversation on GitHub. Already have an account? Sign in to comment