I really appreciated the addition of the Logs and Datasets section in Google AI Studio. However, I see that support for Live models is missing, particularly the gemini-2.5-flash-native-audio-preview-09-2025 model. It would be very helpful if Live Audio Stream models could also be added. Is there any chance that Live models will be added as well?
Thanks again for your valuable work.
Thank you for your feedback. We appreciate you taking the time to share your thoughts with us, and we’ll be filing a feature request.
To help us prioritize this request effectively, any additional details you can provide regarding the impact this feature would have would be very helpful.
Hi @Sonali_Kumari1,
thank you for your feedback. We’re building a commercial application that uses the Gemini Live API. It’s a customer support bot. Having an official log of all sessions would be very helpful. I’m not talking about a log with all the audio transcripts, but at least a reference with the system prompt, tool calls, number of turns, and detailed token consumption.
In particular, I would need official feedback from Google regarding token consumption. In fact, as I reported in this post (Gemini Live API Reports Triple Prompt Token Consumption - #3 by Gianluca_Emaldi) over 20 days ago, the token consumption credited to us is at least 3-4 times higher than the number of tokens we count. So I’d like official feedback to understand what’s happening.
Thank you for your cooperation.