Outage in Retell AI
7% calls got abnormally high latency
Resolved MinorIncident Report
Incident range: 6:30am - 11am PST
impact: around 7% of the calls are having abnormally high latency
post mortem:
Some AWS automatic patches to our transcription clusters caused the container to lost GPU access, and used CPU for transcription, causing extra long latency there. Most calls are routed to the backup endpoint which was working fine, but around 7% did not trigger the fallback there. We are updating the containers to ensure it does not get impacted with the automatic patches.
Need to monitor Retell AI outages?
One place to monitor all your cloud vendors.
Get instant alerts when an outage is detected.
Latest Updates ( sorted recent to last )
RESOLVED
3 months ago - at 10/02/2025 08:27PM
Incident range: 6:30am - 11am PST
impact: around 7% of the calls are having abnormally high latency
post mortem:
Some AWS automatic patches to our transcription clusters caused the container to lost GPU access, and used CPU for transcription, causing extra long latency there. Most calls are routed to the backup endpoint which was working fine, but around 7% did not trigger the fallback there. We are updating the containers to ensure it does not get impacted with the automatic patches.
Latest Retell AI outages
Outbound Calling Service Degradation - 4 days ago
ASR configuration bug - 13 days ago
Call and API failures due to Stripe outage - 28 days ago
Transcription error for non English traffic - about 1 month ago
Telnyx calls encountering telephony provider permission denied - about 2 months ago
The Status Page Aggregator with Early Outage Detection
With IsDown, you can monitor all your critical services' official status pages from one centralized dashboard and receive instant alerts the moment an outage is detected. Say goodbye to constantly checking multiple sites for updates and stay ahead of outages with IsDown.
Start free trialNo credit card required · Cancel anytime · 5350 services available
Integrations with
