Resolved -
This incident has been resolved.
Jul 24, 13:22 UTC
Investigating -
Between approximately 10:55 and 12:00 UTC on July 24, an upstream infrastructure issue in AWS's US-WEST-2 region caused intermittent connectivity problems that may have affected Deepgram services and customer infrastructure — including elevated errors, connection timeouts, and failures fetching remotely hosted media for some requests.
The underlying cause was an AWS networking issue affecting routing to the US-WEST-2 region. AWS applied mitigations and fully restored connectivity by ~12:00 UTC. We have confirmed recovery and are continuing to monitor.
Resolved -
This incident has been resolved.
Jul 21, 15:20 UTC
Investigating -
Starting at 13:45 PM UTC, some Voice Agent sessions using Google/Gemini without a pinned model version received failed responses due to a routing issue introduced in this morning's deploy. Two Gemini models were unaffected; all other providers and products were unaffected. The issue was resolved as of 3:20 PM UTC.
Jul 21, 13:45 UTC