Is AssemblyAI down? › Outage history › Sep 16, 2026

AssemblyAI outage on Sep 16, 2026: what happened

On Sep 16, 2026, the AssemblyAI status page reported "Outage on US Async Endpoint". About 1 hour 15 min: from Sep 16, 2026, 20:22 UTC to Sep 16, 2026, 21:37 UTC, by the official start and resolution times.

AssemblyAI right now

At our last refresh (Oct 22, 2026, 12:35 UTC) AssemblyAI was up: All Systems Operational.

Is AssemblyAI down right now? →
Started
Sep 16, 2026, 20:22 UTC
Resolved
Sep 16, 2026, 21:37 UTC
Duration
1 hour 15 min
Official impact
Critical
Affected
Asynchronous API, APIs - Asynchronous API
Source
Outage on US Async Endpoint on the AssemblyAI status page

The AssemblyAI status page rated it "Critical", its highest impact level: an outage of the affected parts, not only slowness.

What caused the AssemblyAI outage?

"The failure originated in AWS SQS, the managed queuing service our transcription pipeline uses to distribute work. Specifically, the Fair Queues feature began rejecting valid messages with an `InvalidParameterValue` error on a parameter our services had been sending successfully for months."

From the AssemblyAI status page, incident report, Sep 21, 2026, 20:38 UTC.

When was it fixed?

The AssemblyAI status page marked it resolved at Sep 16, 2026, 21:37 UTC, 1 hour 15 min after it started. A fix was in place and being monitored from Sep 16, 2026, 21:12 UTC. Its resolution note: "The issue, which was the result of an AWS service issue, has been resolved and we have continue to see good performance since implementing a fix so we are now closing this issue."

Timeline of official updates

Every update the AssemblyAI status page posted, oldest first. Times are UTC.

  1. Sep 16, 2026, 20:22 UTC investigating

    We are currently investigating an issue that is affecting all customers using our Async API on our US endpoint. Users will be receiving a server error. We will update with more information as we learn more. This began at 8pm UTC.

  2. Sep 16, 2026, 20:24 UTC identified

    The issue has been identified. This is affecting approximately 50% of all async transcriptions on the US endpoint.

  3. Sep 16, 2026, 20:57 UTC identified

    We are continuing to investigate these elevated errors. We will provide an update as soon as possible.

  4. Sep 16, 2026, 21:10 UTC identified

    We are seeing a reduction in the number of errors, but we are still working to fully resolve the issue.

  5. Sep 16, 2026, 21:12 UTC monitoring

    We have mitigated the issue and our Async API service is recovering.

  6. Sep 16, 2026, 21:37 UTC resolved

    The issue, which was the result of an AWS service issue, has been resolved and we have continue to see good performance since implementing a fix so we are now closing this issue.

The official incident report

Published Sep 21, 2026, 20:38 UTC. The opening of the report; the full text is on the official page.

Summary On September 16, 2026, between 20:04 and 21:08 UTC, our US Async API returned elevated server errors. At peak, roughly 50% of async transcription requests on the US endpoint failed, and a portion of the requests that did succeed took longer than usual to complete. Our EU endpoint and real-time/streaming services were not affected. Root cause The failure originated in AWS SQS, the managed queuing service our transcription pipeline uses to distribute work. Specifically, the Fair Queues feature began rejecting valid messages with an `InvalidParameterValue` error on a parameter our services had been sending successfully for months. There was no deploy or infrastructure change on our side that triggered this; AWS confirmed it as a service-side issue and rolled back the change on their end later that evening. Because the affected queues sit in the path between our API and our transcription workers, requests that could not be queued failed outright, and a portion of the work that did get through was delayed behind reduced throughput. We mitigated by disabling Fair Queues across our services and reverting to standard SQS queues, which restored normal operation roughly an hour after the first error. What we're doing about it * Faster configuration changes. Much of our service configuration lives in environment variables, which require task restarts to propagate. We are moving this to a global feature flag system so mitigations like this one take seconds rather than minutes. * Expedited emergency deploys. We are adding a reviewed break-glass path so urgent fixes can bypass non-essential CI steps. * Multi-region failover. We are prioritizing work to fail the US pipeline over to a second region when a regional provider dependency degrades, rather than relying on ...

Read the full report on the AssemblyAI status page

AssemblyAI outage questions

What caused the AssemblyAI outage on Sep 16, 2026?

In its incident report (Sep 21, 2026, 20:38 UTC), the AssemblyAI status page said: "The failure originated in AWS SQS, the managed queuing service our transcription pipeline uses to distribute work. Specifically, the Fair Queues feature began rejecting valid messages with an `InvalidParameterValue` error on a parameter our services had been sending successfully for months."

When was the AssemblyAI outage on Sep 16, 2026 fixed?

The AssemblyAI status page marked it resolved at Sep 16, 2026, 21:37 UTC, 1 hour 15 min after it started. A fix was in place and being monitored from Sep 16, 2026, 21:12 UTC. Its resolution note: "The issue, which was the result of an AWS service issue, has been resolved and we have continue to see good performance since implementing a fix so we are now closing this issue."

How long did the AssemblyAI outage last?

About 1 hour 15 min: from Sep 16, 2026, 20:22 UTC to Sep 16, 2026, 21:37 UTC, by the official start and resolution times.

Was AssemblyAI completely down?

The AssemblyAI status page rated it "Critical", its highest impact level: an outage of the affected parts, not only slowness. The affected parts listed were: Asynchronous API, APIs - Asynchronous API.

Which parts of AssemblyAI were affected?

The AssemblyAI status page listed: Asynchronous API, APIs - Asynchronous API.

Other recent AssemblyAI incidents

Full AssemblyAI outage history and biggest outages → · Recent outages across all services →

Quotes are the AssemblyAI status page's own words, from the official incident. Is It Up or Down is independent and not affiliated with AssemblyAI. Times are UTC.