Genesys Cloud - Developer Community!

Hello,

I'm exploring the media server capabilities and would appreciate some guidance.

My goal is to:

• Access a real-time audio stream from a live call (or a real-time transcription of the conversation),

• Use AI to generate a response based on the caller's input,

• And then stream the AI-generated response back to the caller - either:

  • By sending a text stream to the media server for text-to-speech conversion, or

  • By streaming pre-generated audio directly into the call.

My key questions are:

1. Is there a way to use the API to access a raw real-time audio stream that I can process directly?

2. If not, what alternative approaches would you recommend to achieve this real-time, AI-assisted interaction workflow?

Thanks in advance for your help!