Closed RealtimeGraphX closed 1 year ago
@RealtimeGraphX Thanks for your feedback! We will investigate and update as appropriate.
Hi @RealtimeGraphX According to the documentation, visemes are currently supported only for the en-US (US English) neural voices. However, the neural voices are multilingual and fluent in their own language and English. If the input text in English is spoken with a Spanish accent, for example, you can use the es-ES-Elvira Neural voice. If the voice does not speak the language of the input text, the Speech service won't output synthesized audio.
For viseme generation will be available for other languages in the future, I'd recommend working closer with our support team via an [Azure support request] (https://docs.microsoft.com/en-us/azure/azure-portal/supportability/how-to-create-azure-support-request). Or you can leverage our Q&A forum by posting your issue there so our community, and MVPs can further assist you in troubleshooting this issue or finding potential workarounds. [Teams Q&A forum] (https://docs.microsoft.com/en-us/answers/topics/46488/office-teams-windows-itpro.html) for technical questions about the configuration and administration of Microsoft Teams on Windows. [Microsoft Teams Community forum] (https://answers.microsoft.com/en-us/msteams/forum?sort=LastReplyDate&dir=Desc&tab=All&status=all&mod=&modAge=&advFil=&postedAfter=&postedBefore=&threadType=All&isFilterExpanded=false&page=1
Hi @Naveenommi-MSFT Thanks for your response. Using the US neural voices for other languages unfortunately yields very bad audio synthesis results, so its not really a solution. If I understand you correctly, making viseme generation available for other languages is not being in active development right now?
@RealtimeGraphX Thank you for Reply. I've delegated this to content author @yulin-li, who will review it and offer their insightful opinions.
@yulin-li Could you please review add comments on this, update as appropriate.
@yulin-li Do you have any update on that? Or should I create an Azure support request for that question? Thanks a lot. :-) Best, Rudi
Hi, sorry for the late reply. Which kind of viseme are you using? Viseme ID or blendshape?
I am using the blendshapes for animation (3D character in Unreal Engine)
OK thanks, then we can support more locales such as it-it
, de-de
, fr-fr
, and es-es
. I will update the ETA when I get.
That sounds wonderful! Really looking forward to that. Thanks a lot for the quick reaction, and yes please let me know about the progress. :-)
I noticed visemes for de-DE-KatjaNeural (female) is available but not de-DE-ConradNeural (male) - is that a known error? since the ConradNeural responds visemes as well, but just empty strings!
Hi @Zaniyar, for now ConradNeural
doesn't support blendshape. But we will add it soon.
Hi @Zaniyar, for now
ConradNeural
doesn't support blendshape. But we will add it soon.
Any other German male model with blendshapes?
I don't think this issue can be closed yet @eric-urban. @yulin-li promised to update on the ETA of support for other languages. There has not been any update yet. I accidentally learned that there already is some support for a German voice, thanks to @Zaniyar . An official info from the developers would be great.
@RealtimeGraphX Unfortunately only female voice. Are there maybe other companies providing a viseme API for German?
@Zaniyar I am not sure about other viseme generation solutions. There must be other options. But I am sure, Microsoft is working on that. Would be sad to miss out on this opportunity.
@Zaniyar I am not sure about other viseme generation solutions. There must be other options. But I am sure, Microsoft is working on that. Would be sad to miss out on this opportunity.
at least the programmer here are not really interested into that topic - they already closed the issue lol
I tried vsiemes for some Indian languages. It works for Hindi, Tamil and Telugu but not for Bengali or Kannada. Is there a way to know for what languages they work?
We have the doc saying blendshape is supported in which languages. If you are asking for feature support, we can add them in about one month
Hi! I would like to ask whether viseme generation will be available for other languages apart from English and Chinese? We are currently building an application where we rely on Azure Speech for STT, TTS and visemes. There are already customers who request language support for Italian, German, French and Spanish. Is this something that is being currently developed? Best regards, Rudi
Document Details
⚠ Do not edit this section. It is required for learn.microsoft.com ➟ GitHub issue linking.