Integrating Convai with Make for Avatar Speech Processing

Hello, everyone!

I’m working on an integration where I need to intercept the user’s input in Convai, send it to a Webhook in Make for processing, and then return the response so the avatar can speak the processed message.

My main questions are:

  • Is there a specific event within ConvoAI to capture the recognized text before it’s sent to TTS?
  • Is it possible to modify this flow to send the text to a Webhook and return the response for the avatar to speak?
  • What Blueprint or configuration would be most suitable for this approach?

I really appreciate any help!