I am using Gemini 2.0 Flash Experimental model with Audio output and getting “An internal error has occurred.” error message.
On looking at the GenerateContent API response, it says “[,[3,“Model does not support requested modality: AUDIO”]]”.
Stream realtime is working fine for me but create prompt option is failing every time. No other model has an audio output option. Text is also working fine but “Image and Text” is also returning the same error.
Please let me know if I am missing anything. Any help is appreciated.