Hi all,
I am trying to create an agent using Google agent development kit with vertex ai that can create a multi speaker audio.
Googles documentation has been very confusing about whether or not Gemini 2.5 flash and pro tts models in preview supports multi speaker audio through vertex ai.
Does any one know if this is supported and if yes then is there an example code that I can refer to.
So far I think only ai studio has that support.
Hi Ankit, i have been trying the same to achieve but im constantly getting rate limit error please gimme clarity about api key what api key do i need to provide is it the free gemini api key or billing activated console project vertex api enabled api key?
Hi Surya,
I have a GCP project and my api key is created under that from AI Studio.
Free api key should have rate limits for obvious reasons.
Hello,
Welcome to the Forum,
To answer your query, multi-speaker support is available with Gemini 2.5 Flash. We recommend checking the speech generation section in the Gemini API docs for more details.