Is AssemblyAI down?

We are currently investigating an issue where users on our us-east-1 endpoint are experiencing 503 errors when using temporary tokens with our Realtime API.

Our team has identified the issue and a fix is being released.

We are continuing to work on a fix for the issue. The API is stable and the errors subsided at 5:11pm UTC.

A fix has been implemented and we are monitoring the results.

This incident has been resolved.

This incident affected a subset of Universal-3.5 Pro streaming sessions in the us-east region on July 31 between 20:15 and 22:15 UTC. Affected sessions connected successfully but did not process incoming audio, so no transcript was returned while the connection remained open. Other regions, other streaming models, and our asynchronous API were unaffected. We apologize for the disruption to your workflows. If you have any questions, please reach out to [email protected].

We are seeing increased processing times for pre-recorded (async) transcriptions on the US endpoint. Webhook deliveries may also be delayed. We are currently investigating.

We have identified the issue causing elevated processing times for async transcriptions on the US endpoint and have addressed the root cause. The system is recovering, but processing times remain elevated while the backlog clears. Webhook deliveries may also continue to be delayed.

We have been monitoring the queue drain and transcription pickup delays caused by the backlog. Processing times are returning to normal ranges on the US endpoint and the backlog has cleared. We are continuing to monitor.

This incident has been resolved. Async transcription processing times on the US endpoint have returned to normal ranges and webhook deliveries are operating normally.

Incident window: July 7, 2026, 15:00 to 15:10 UTC During this window, newly created Universal Streaming English sessions in the us-west region were degraded. Affected sessions were cancelled with error code 3005 shortly after connecting and did not return transcripts. Sessions already in progress, other regions, other streaming models, and all other services were unaffected. The cause was insufficient compute capacity after a scaling schedule failed to execute ahead of a traffic spike. Capacity recovered at 15:10 UTC and service returned to normal. Sessions affected during this window can be re-submitted and will process normally. If you have any questions, please reach out to [email protected].

We are currently investigating an issue with async transcriptions on the US endpoint that use speaker labels. This is resulting in timeouts for all transcriptions with speaker labels enabled for files under 5 minutes long.

The issue has been identified and a fix has been released.

A fix has been implemented and our API is slowly beginning to recover normal processing.

The root cause has been addressed and our system is slowly working through the transcript backlog, which is causing slower processing on our US async endpoint.

Our API is continuing to recover and incoming transcriptions are returning to normal processing. We are continuing to monitor the situation.

This incident has been resolved.

**What happened** An issue related to our speaker diarization service caused certain requests to hang until they timed out. This lead to a backlog of requests to our async API creating a processing queue across our US transcription pipeline, which slowed and timed out transcription requests more broadly, including requests that were not using speaker diarization. --- **When** Impact ran from approximately 15:00 to 16:25 UTC on June 25, 2026 \(about 1 hour 25 minutes\). The most severe disruption was in the first 45 minutes \(15:00–15:45 UTC\); remaining delays and timeouts cleared shortly after. Full recovery was confirmed by ≈16:40 UTC. --- **What services were affected** On our US async API endpoint transcription requests during this window saw processing delays and timeouts. Our EU async API endpoint was not affected and operated normally throughout.