Audio transcript in Gemini Live API not really working

[tjasmin111]

Description of the bug:

I'm trying to add transcription to the Gemini Live demo code here. According to Google's official capability: https://ai.google.dev/gemini-api/docs/live-guide#audio-transcription

But the transcription is a mess, like below. Am I missing anything? Any extra flags to set?

[Model Transcript]:  Ca
[Model Transcript]: n I
[Model Transcript]:  pl
[Model Transcript]: eas
[Model Transcript]: e h
[Model Transcript]: ave
[Model Transcript]:  yo
[Model Transcript]: ur
[Model Transcript]: acc
[Model Transcript]: oun
[Model Transcript]: t n
[Model Transcript]: umb
[Model Transcript]: er

Actual vs expected behavior:

I'm expecting it clearly writes: Can I please have your account number. This is how Amazon's Nova Sonic works.

Any other information you'd like to share?

No response