I am using the new gemini 2.0 live API, and using Audio to Audio. I’m noticing that when I return information from a function call the model doesn’t seem to see that information. I was reading that this is an async operation, is there a way to force the live api to wait to generate it’s next audio response until the tool call is complete?
Could you share the code you’re using?
Related topics
| Topic | Replies | Views | Activity | |
|---|---|---|---|---|
| Google Live API | 0 | 120 | February 15, 2026 | |
| Gemini Live API Tool Calling Issues – Inconsistent Behavior and Empty Tool Responses | 8 | 1319 | June 20, 2025 | |
| Anybody succeeding in making Gemini say something before calling functions? | 3 | 331 | June 3, 2026 | |
| Gemini 2.5 flash native audio dialog (LIVE/Multimodal API) Tool Calling | 7 | 986 | September 23, 2025 | |
| Problems with Live API Audio Streaming and Function Responses | 3 | 661 | July 5, 2025 |