Transcription streaming along with Audio parts responses

[mandroidV2]

Description of the feature request:

HI
is it possible to get the transcriptions stream along with returned audio parts? I tried to set audio and text in response modalities but it didn't work.
Thanks!

What problem are you trying to solve with this feature?

I would want to show a transcript in the real time for the audio output

Any other information you'd like to share?

No response

[hapticdata]

Hi, it is currently not possible for the model to return both text and audio tokens. If you need this functionality immediately your best option is to receive text tokens and stream those into another speech-to-text system such as google/speech-to-text