Discussions

Ask a Question
Back to All

Text-to-Speech Stream Endpoint

Hello everyone, I am developing an app for kiosk screens. In my app, I want to greet the user with a "hello" when the camera detects a face. To achieve this, I need text-to-speech (TTS) for streams or to create a custom video. I have checked the documentation but couldn't find TTS support for streams. What should I do? Thanks!