I am playing around with Azure real-time TTS avatar, and for my use case I don’t want the activation of speech synthesize to be controlled by the frontend web application.
I want the streamed TTS avatar to be activated from another backend service that just send rest calls to the TTS service with whatever text the avatar needs to synthesize.
However I have been unable to find a way to do so and can only find documentation for how to operate the TTS avatar through websockets from the frontend web app with microsoft-cognitiveservices-speech-sdk.AvatarSynthesizer.
Do anyone know if microsoft has an rest rendpoint that can synthesize speech to an open TTS avatar websocket stream given its ID?
Benjamin is a new contributor to this site. Take care in asking for clarification, commenting, and answering.
Check out our Code of Conduct.