# How to fix Latency (3 secs) of Gemini 3.1 Flash Live

**URL:** <https://community.livekit.io/t/how-to-fix-latency-3-secs-of-gemini-3-1-flash-live/766>\
**Category:** Telephony\
**Tags:** other, gemini\
**Created:** [April 3, 2026, 2:57am UTC](https://community.livekit.io/t/how-to-fix-latency-3-secs-of-gemini-3-1-flash-live/766 "2026-04-03T02:57:22Z")\
**Posts on this page:** 2\
**Page:** 1

<div class="post-metadata">

**Author:** ![Harvinder\_Singh](https://sea1.discourse-cdn.com/flex001/user_avatar/community.livekit.io/harvinder_singh/32/927_2.png) [@Harvinder\_Singh](https://community.livekit.io/u/Harvinder_Singh)\
**Post date:** [April 3, 2026, 2:57am UTC](https://community.livekit.io/t/how-to-fix-latency-3-secs-of-gemini-3-1-flash-live/766/1 "2026-04-03T02:57:22Z")

</div>

If you use the Gemini + LiveKit plugin directly, you’ll likely experience high latency. In my case, it was around **3-3.5 seconds**.

After deeper investigation, I found that the **TTFP (Time to First Token)** was the main issue—it was sitting at **~2 to 2.5 seconds** , which is extremely high.

Digging further, the root cause turned out to be **enabled tools** , specifically the **Google Search tool**. These tools significantly slow down the agent.

The fix is simple once you identify it:

- **Remove search tools**

There is currently **no clear mention in documentation** that these tools can cause such high latency, which makes this issue harder to diagnose.

Additionally, I’ve seen some discussions suggesting that **disabling noise cancellation** may help. I haven’t fully verified this, but removing search tools definitely has a major impact.

After removing them:

- **TTFP dropped from ~2–2.5 seconds to ~100 ms (overall timeline 1 to 1.5 seconds)**

This improvement is because the model is **speech-to-speech** and can start generating output tokens **before the speaker finishes speaking**. In some cases, this can even result in **negative latency values** , which is ideal for real-time systems.

### Conclusion

To significantly reduce latency:

- Remove **search tools**

- Optionally test disabling **noise cancellation**

This alone can dramatically improve responsiveness.

---

<div class="post-metadata">

**Author:** ![darryncampbell](https://sea1.discourse-cdn.com/flex001/user_avatar/community.livekit.io/darryncampbell/32/20_2.png) [@darryncampbell](https://community.livekit.io/u/darryncampbell)\
**Post date:** [April 3, 2026, 8:39am UTC](https://community.livekit.io/t/how-to-fix-latency-3-secs-of-gemini-3-1-flash-live/766/2 "2026-04-03T08:39:10Z")

</div>

Search tools make sense, [Google Gemini LLM | LiveKit Documentation](https://docs.livekit.io/agents/models/llm/gemini/#provider-tools) , I can imagine scenarios where the tool is overly aggressive and performs too many calls, or unnecessary calls. I haven’t tried it myself, and they are still marked as `experimental`.

I don’t think noise cancellation would be a contributor though, we actually in the docs ([for Krisp](https://docs.livekit.io/transport/media/noise-cancellation/#agents-krisp)) that there is ‘…negligible impact on audio latency…’. You do say this is anecdotal though, so I’ll keep my eyes out for other reports.
