Is AssemblyAI down?

Resolved: Between 23:30 and 23:37 UTC on September 13, 2026, async transcription requests experienced elevated turnaround times due to an unexpected spike in processing load. We scaled out additional capacity and turnaround times returned to normal levels. Requests submitted during this window were processed, with some taking longer than usual to complete.

We are currently investigating an issue where there is increased latency for our Universal 3.5 Pro Realtime model on the US endpoint. This began at 3:15pm UTC.

The issue has been identified and our team is working on a fix.

The fix has been implemented and latency has recovered as of 3:45pm UTC. The team is continuing to monitor the situation.

This incident has been resolved. From 3:15p-3:45p UTC customers experienced increased latency when using our Universal 3.5 Pro Realtime model on the US endpoint. The EU endpoint was not affected. Sessions continued to function during this time without any errors.

We’re seeing elevated latency and errors on async transcription submissions, and our on-call team is actively investigating. Capacity is scaling out now, and we’re monitoring recovery.

We have identified the cause of the elevated error rates affecting asynchronous transcription requests. Our engineering team is actively restoring capacity, and error rates should improve as this completes. We will continue to provide updates as more information becomes available.

A fix has been implemented and we are monitoring recovery.

This incident has been resolved. Between approximately 13:40 and 14:40 UTC, asynchronous transcription requests on our US endpoint experienced elevated latency and errors. Processing times and error rates have returned to normal ranges and the backlog has cleared.

We're currently investigating an issue affecting users on our Universal 3.5 Pro Realtime model, where new streaming sessions could not be created on our EU endpoint. This occurred from 13:00–13:12 UTC. Affected users are seeing a 3005 close code. Users on the US endpoint are unaffected.

The issue has been identified and a fix is being implemented.

A fix has been implemented and our team is monitoring the results. Users can now create new realtime sessions successfully.

We are continuing to monitor for any further issues.

This incident has been resolved.

We're currently seeing longer than usual processing times for asynchronous transcription requests using Universal-3 Pro and Universal-3.5 Pro. Requests are being accepted and are completing, but time to completion is elevated while our queues work through a backlog.

We have identified the cause of the elevated processing times affecting pre-recorded transcription requests using Universal-3 Pro and Universal-3.5 Pro. Our engineering team has addressed a capacity constraint and is working to restore full capacity. Processing times will remain elevated while the backlog clears, and some customers may see requests queued or throttled. We will continue to provide updates as more information becomes available.

Processing times for pre-recorded transcription requests using Universal-3 Pro and Universal-3.5 Pro are returning to normal ranges and the backlog has largely cleared. We are continuing to monitor to ensure stability.

This incident has been resolved. Processing times for pre-recorded transcription requests using Universal-3 Pro and Universal-3.5 Pro have returned to normal ranges and the backlog has cleared.