search

MicrosoftDocs / azure-docs

Open source documentation of Microsoft Azure
https://docs.microsoft.com/azure
Creative Commons Attribution 4.0 International
10.08k stars 21.13k forks source link

Text to Speech Avatar in Teams bot #122555

Open shilpaCM opened 1 month ago

shilpaCM commented 1 month ago

Hi,

Part of our project requirement we need render Text to Speech Avatar in teams bot & add additional functionality for TTS Avatar. Any one working on the integrating TTS Avatar in teams or Any pointers will be helpful.

Document Details

⚠ Do not edit this section. It is required for learn.microsoft.com ➟ GitHub issue linking.

PesalaPavan commented 1 month ago

@shilpaCM It would be great if you could add a link to the documentation you are following for these steps? This would help us redirect the issue to the appropriate team. Thanks!!

PesalaPavan commented 1 month ago

@shilpaCM We are going to close this thread but if there are any further questions regarding the documentation, please tag me in your reply and we will be happy to continue the conversation.

shilpaCM commented 1 month ago

Hi @PesalaPavan,

i am following official documentation for TTS Avatar, but trying to get part of Teams Bot. https://learn.microsoft.com/en-us/azure/ai-services/speech-service/text-to-speech-avatar/what-is-text-to-speech-avatar

PesalaPavan commented 3 weeks ago

@shilpaCM Thanks for your feedback! I've assigned this issue to the author who will investigate and update as appropriate.

antoniosmakro commented 2 weeks ago

Hi @shilpaCM ,

I assume you want to integrate TTS Avatar with Open AI services, too, and render in real-time. I think you'll need access to the Bot's media streams, which can be achieved with Microsoft's Graph Communications Calling SDK ..an SDK that's quite old and not for the faint-hearted.

Real-time media for Teams bots: https://learn.microsoft.com/en-us/microsoftteams/platform/bots/calls-and-meetings/real-time-media-concepts Graph Communications docs: https://microsoftgraph.github.io/microsoft-graph-comms-samples/docs/ GitHub Samples: https://github.com/microsoftgraph/microsoft-graph-comms-samples/blob/master/Samples/V1.0Samples/LocalMediaSamples/README.md

Microsoft has some TTS Avatar real-time streaming samples for Python and JS but not for .NET. You could probably modify their batch sample code for real-time here: https://github.com/Azure-Samples/cognitive-services-speech-sdk/tree/master/samples/batch-avatar/csharp/BatchAvatarSample