Outage recap · Deepgram

Deepgram outage — September 28, 2026

On September 28, 2026, Deepgram had 2 reported incidents on Deepgram's official status page. Below is what was reported — impact, timing, and the AI services the same upstream outage could affect.

Elevated latency on Flux STT (US)

minor
Started
Sep 28, 1:04 PM EDT
Resolved
Sep 28, 1:07 PM EDT
Duration
4 min

Deepgram's updates (2)

  1. investigating · Sep 28, 1:04 PM EDT

    We are investigating an issue with Flux STT that may result in some US connections to see delayed transcripts and some disconnects.

  2. resolved · Sep 28, 1:07 PM EDT

    This incident has been resolved.

What our checks recorded

We checked Deepgram 1 time from Deepgram's start time to its resolution, once every five minutes. Every one of them reached Deepgram's site, so this incident did not show up as a failed page load. Our check loads the public site; it cannot see an API error or a broken feature. Median response time was 199 ms, against 145 ms over the 24 hours before. Deepgram posted the incident at Sep 28, 1:04 PM EDT.

Updates are Deepgram's own words from its status page (status: resolved); we never add an inferred cause. The vendor's incident page ↗

Elevated Latency and Errors for Batch STT (US)

minor
Started
Sep 28, 1:40 PM EDT
Resolved
Sep 28, 1:53 PM EDT
Duration
13 min

Deepgram's updates (2)

  1. investigating · Sep 28, 1:40 PM EDT

    We are investigating elevated latency and 429 errors affecting some pre-recorded (batch) STT requests.

  2. resolved · Sep 28, 1:53 PM EDT

    An issue affecting some of our pre-recorded transcription servers slowed request processing. As requests took longer to complete, some customers saw elevated latency or received 429 errors. We identified and mitigated the issue, service has returned to normal.

What our checks recorded

We checked Deepgram 2 times from Deepgram's start time to its resolution, once every five minutes. Every one of them reached Deepgram's site, so this incident did not show up as a failed page load. Our check loads the public site; it cannot see an API error or a broken feature. Median response time was 117 ms, against 144 ms over the 24 hours before. Deepgram posted the incident at Sep 28, 1:40 PM EDT.

Updates are Deepgram's own words from its status page (status: resolved); we never add an inferred cause. The vendor's incident page ↗

AIDownCheck is not affiliated with Deepgram. This recap summarizes incidents published on Deepgram's official status page.