Receive both audio and text from live api

[margielamob]

Description of the feature request:

is it currently possible to receive both the text and audio response?

What problem are you trying to solve with this feature?

I would like to catch the result of the google search and be able to overlay it to the user into a text format

Any other information you'd like to share?

No response

[andycandy]

Is there a specific reason you're looking for an audio response in this case? If you're aiming to extract and display search results in text, wouldn't using search grounding get you what you need more directly?

Possibly I’m missing the bigger picture here, mind elaborating on the use case — would love to understand the motive better to be able to help you.

[margielamob]

You understood it well. I tried to use grounding_metadata = getattr(server_content, 'grounding_metadata', None) if grounding_metadata is not None: display.display( display.HTML(grounding_metadata.search_entry_point.rendered_content)) in the receive_audio function of the Get_started_LiveAPI.py cookbook but the grounding_metadata is always None even when the tools are being used.

[andycandy]

Got it, thanks for clarifying that. I haven’t tested this path deeply myself yet, but I’ll take a proper look and get back once I’ve gone through it thoroughly. Appreciate you pointing it out!

[Gunand3043]

Hey @margielamob , You should be able to obtain audio transcription by passing output_audio_transcription in the config parameter. Here is the documentation link for reference.

Thanks

[github-actions[bot]]

Marking this issue as stale since it has been open for 14 days with no activity. This issue will be closed if no further activity occurs.

[github-actions[bot]]

This issue was closed because it has been inactive for 27 days. Please post a new issue if you need further assistance. Thanks!