Add the Text output for GeminiMultimodalLiveLLMService

[fatwang2]

Description

Is this reporting a bug or feature request?
feature

Will you think about change the response_modalities of the output of Gemini, so we can use the output to other tts service.

It will output by text only if you change it to TEXT.

[markbackman]

@fatwang2 can you clarify? Do you want audio input and text output?

[fatwang2]

yes, so that I can transfer to other TTS to support multi languages, I have finished it on my own git Mark Backman ***@***.***>于2024年12月22日 周日22:49写道：

…

@fatwang2 <https://github.com/fatwang2> can you clarify? Do you want audio input and text output? — Reply to this email directly, view it on GitHub <#892 (comment)>, or unsubscribe <https://github.com/notifications/unsubscribe-auth/A77NZSX4M6O6UI72XHABHXD2G3GODAVCNFSM6AAAAABT5N2KOSVHI2DSMVQWIX3LMV43OSLTON2WKQ3PNVWWK3TUHMZDKNJYGQ4DAOBYGY> . You are receiving this because you were mentioned.Message ID: ***@***.***>

[golbin]

I also wish for this feature. I believe it’s very powerful and represents the future.

Any audio input -> transcript text & generated text -> any potential post processing