We’re currently experiencing a timing issue on the first node where the initial response is delayed by ~8 seconds.
This is not expected behavior and was not present before , our system is designed to respond immediately and handle bookings efficiently.
We’re actively investigating the issue. I’ll update this thread once the timing problem is resolved.
If anyone tests the flow in the meantime, please note that this 8-second delay will not be present in normal operation.
If your end-to-end latency P90 exceeds 3 seconds, you should follow these troubleshooting steps:(1)
Check Estimated Latency
Look for features marked with a turtle icon 
in your configuration and check if your estimated latency is higher than 1.5s.(1) If high, disable some features to reduce latency.(1)
Monitor LLM Response Time
Check your current LLM latency and compare against the normal range of 500ms - 900ms.(1) If consistently above 900ms, use fast tier, switch to an alternative LLM provider, or wait for your current provider to resolve performance issues.(1)
Check Status Page
Check the Status Page for any ongoing issues.(1) If there are any ongoing issues, wait for them to resolve.(1)
Consider Geographic Distance
International phone calls may introduce additional latency due to geographic distance.(1) Consider getting a local phone number in the same region as your users.(1)
Contact Support
If the above steps don’t resolve your latency issues, locate your call ID and message the support-questions channel in the Discord community.(1) Include your call ID, steps you’ve already tried, and current latency measurements.(1)
Retell AI guarantees > 99.9% uptime and maintains 24/7 latency monitoring and alerting systems to catch and address issues before they impact operations.(2)
Hello @Belvoro_AI
There was an issue with node transitions, and it should be fixed now.
Please try again.