Sometimes the transcript is putting the assistant response into the user message. We have the

modelOutputInMessagesEnabled

set to true because we don't want a transcription to run from the TTS output. It still seems like it is trying to transcribe that audio, though, and we wonder if this is what is causing the issue.

Hey! To help track down this issue, could you share: \- The call ID \- When exactly this happened (the timestamp) \- What response you expected to get \- What response you actually got instead This would really help us figure out what went wrong!

I am thinking this is working once we use an 11Labs voice model. I am not seeing this happen in those logs. I am trying to find a previous call to show exactly where this was. But wiht 11Labs we are facing some major latency that has been an issue. I mention it here if we could get some help to really resolve this issue https://discord.com/channels/1211482211119796234/1413204474767478949

Hey Noah, thanks for sharing your details. Our team will look into it and get back to you soon with an update.

Thank you!

Could you share any additional call IDs with timestamps? That way, our team can investigate further.

I will try to find more specific instances of that

Hey, I'm closing this ticket now. Let me know if you need anything else.