### Answer If you're experiencing latency above 1000ms with Google Flash 3.0, here are some troubleshooting steps: 1. Check Estimated Latency - Look for features marked with a turtle icon 🐢 in your configuration, as certain settings increase latency [(1) ]() [(2) ]() - Check if your estimated latency is higher than 1.5s in the agent detail page under "Estimated Latency" - If high, disable some features to reduce latency [(1) ]() 2. Monitor LLM Response Time - Compare your LLM latency against the normal range (500ms - 900ms) - If consistently above 900ms, consider using the [fast tier]() or switching to an alternative LLM provider 3. Additional Checks - Verify no ongoing issues on the [Status Page]() - Consider geographic distance—international calls may introduce additional latency - Make sure "disabled transcript formatting" is toggled off, as this setting can incur latency [(3) ]() 4. Contact Support If the above steps don't resolve the issue, message the support-questions channel in Discord with your call ID, steps you've tried, and current latency measurements [(1) ]() Production voice AI agents typically aim for 800ms or lower latency to maintain conversational flow [(4) ]() [(5) ]()

​ To learn more, see the sources I considered: [[1] Troubleshoot high latency](https://docs.retellai.com/reliability/troubleshoot-latency) [[2] Check estimated latency](https://docs.retellai.com/reliability/check-estimated-latency) [[3] High latency (>3500ms)](https://discord.com/channels/1186424376300679209/1296580769766178816) [[4] ](https://www.retellai.com/resources/ai-voice-agent-latency-face-off-2025) [[5] ](https://www.retellai.com/resources/sub-second-latency-voice-assistants-benchmarks) ​

Feel free to tag @AI Evy with additional questions. I also appreciate feedback, it helps me improve.