Previous incidents

We identified the issue as a misconfiguration in the read-API endpoint. The fix has been applied, and all call logs should now display correctly. No data was lost.

Affected call logs have been successfully restored. We will providing a detailed RCA soon.

Cloudflare has resolved their issues and our services are restored.

We have temporarily increased our concurrency limits with provider and working on a long term solution.

concurrency limit has been reset and jobs are processing normally. issue has been resolved as of 9:05 PT

Our STT provider has made a fix on their end and are reporting improvement. We are continuing to monitor while we push out our own improvement: https://status.deepgram.com/incidents/vgsyqxkc67by.

Issue has been mitigated as of 2:50 AM PT

Nov 7th 2025 SIP service degradation

Summary

On Friday, November 7th, 2025, one of our SIP gateway experienced a failure, causing inbound and outbound Vapi SIP calls to be disrupted between 10:30 AM and 12:15 PM PST

Context

All Vapi SIP calls go through our SIP infrastructure which handles SIP trunking, authentication, and registration. When an inbound SIP call arrives, the SIP SBC authenticates and validates it, making a webhook call to our API server for call registr...

We are working on RCA for SIP degradation, we will share it by November 12th

We experienced a spike in call connection errors between 3:40 and 3:58. The issue has since been resolved.

We are seeing increased latency and requests timing out from API and DB degradation. We are working with our DB provider to resolve this, and have made a change.

Now monitoring to ensure improvement.

There was a DB restart and things are looking normal now. The issues have been resolved.

we experienced elevated errors in our api (for phone calls create) at 9:35 AM PT for few minutes. This has been resolved.

We had a restart on our database endpoint leading to a small blip in 500s for api endpoints.

We had a small blip on daily channel with call.in-progress.error-vapifault-worker-died errors due to a new daily deployment. We have rolled it back.

The issue with twilio inbound calls failing on daily has been resolved. The root cause was connection timeouts on a new egress proxy service.

We detected calls logs not reflecting in the dashboard for some time. This was due to an error while attaching a partition and has been resolved now. Call logs will be populated soon if they were missing.

After further investigation with our WebRTC provider, this does not seem to be platform issue. We will follow up with impacted users directly.

We experienced intermittent spikes in 5xx errors on our APIs in the weekly cluster. The root cause was identified, and a fix has already been implemented.

During this period, both inbound and outbound calls may have been affected, as they rely on the APIs for data, resulting in potential service degradation.

Services are restored.

Problem has been resolved now. All services are healthy again.

We have fixed the issue. Call Logs are returned correctly by API

Cartesia has resolved the issue, and is full operational.

We have identified the root cause. The problem has been fixed by rolling back a recent deployment on daily.

We have scaled up our telephony infrastructure resources and bumped our rate limits. We haven't seen any more issues in the last 20 minutes, and call transfers are working as expected now. We are closely monitoring.