I'm trying to figure out why, for the transcript, the LLM output is sent to the speech-to-text. Why not just directly send me the LLM output? Is this a setting I can configure? We're building out a third-party web widget that's pulling in the transcript, and it's taking it from the speech-to-text. It would be better to just give us the exact LLM output, and I can't figure out how to just get that exactly, the actual LLM output. So I could put that into my transcript for the user.

Hi Qper, It seems there isn't a clear support request included. Could you please provide more details about your current issue or question? This will help me assist you more effectively.

I actually figured it out thanks

Hey, I'm looking into something similar. Do you mind describing your solution?

We found that there is a model output first

@Qper were you able to find a way for the model to use the previous output, instead of agent transcription which can have errors?

Use

modelOutputInMessagesEnabled

: