I’ve identified an issue with Stream Realtime’s text-to-speech functionality. Specifically, the system does not insert natural pauses following punctuation marks (e.g., commas, periods). Consequently, the output becomes a continuous stream of words, delivered at an uncomfortably high tempo, effectively forming a single, unbroken sentence.
Hi @Y_Yalcin ,
Welcome to the Forum !!
Thank you for reporting this .
Could you please let us know which Gemini model you are using ?