Deepgram Voice AI had 34 outages in the last 2 years totaling 12h 38m of downtime — averaging 1.4 incidents per month.
There were 34 Deepgram Voice AI outages since July 24, 2025 totaling 12h 38m of downtime. Each is summarised below — incident details, duration, and resolution information.
Start: 16:15:00 UTC End: 17:18:00 UTC Streaming connectivity issues from some AWS regions may have caused Websocket failures errors and degraded connectivity
We've identified an issue with an upstream network provider across various US regions, and are working to shift traffic to alternative routes.
The issue has been mitigated after rerouting traffic to avoid upstream network provider failures. Networking errors may have occurred intermittently between 12:08 am UTC and 1:51 am UTC.
This incident has been resolved.
We're experiencing an elevated level of API errors for streaming and batch STT and batch TTS - are currently looking into the issue.
Streaming and batch STT and TTS requests experienced elevated error rates due to connectivity issues in one of our regions that caused services to stop and not restart as expected. The issue has been resolved, and current status of the Deepgram API is operational.
We are currently investigating elevated error rates returned from STT batch requests.
Elevated error rates were observed for requests that submitted a URL to an input audio file or used callbacks to collect the response, primarily affecting STT batch requests.
We are investigating an issue where a subset of requests may return elevated rates of 5XX errors or experience significantly higher time to first byte.
This incident has been resolved.
We are investigating an issue that may result in callback failures and timeouts.
This incident has been resolved.
Between 2025-08-14 21:13 UTC and 2025-08-14 21:37 UTC, the Voice Agent API experienced a 20-minute outage that prevented all new connections from being established. Existing active connections were not impacted. The issue has been resolved, and current status of the Voice Agent API is operational.
- High rate of callback failures
- Service degradation in inference infrastructure - High rate of premature streaming text-to-speech