Is AssemblyAI down?

We've identified an issue causing a significant portion of pre-recorded transcription requests using Universal-3.5 Pro and Universal-3.6 Pro to fail or take longer than usual to complete, across all regions. Streaming is not affected. We've identified the cause and are rolling back a recent change, and we're beginning to see recovery.

Error rates are decreasing as our rollback progresses, and we're continuing to work on fully resolving the issue. Some requests may still fail or take longer than usual to complete.

We've applied a fix and error rates have dropped significantly. Some pre-recorded requests using Universal-3 Pro, Universal-3.5 Pro and Universal-3.6 Pro may still take longer than usual to complete while we work through the backlog.

Error rates and processing times have returned to normal. We're monitoring to make sure performance remains stable.

We have continued to see good performance after the rollback, and error rates and processing times have remained in the normal ranges. We are now marking this issue as resolved. Any requests that returned an error during this incident can be safely resubmitted.

We have identified an issue with a recent change to temporary tokens that is causing some Real-time STT sessions that use temp tokens to fail with a 502 error. Our team is actively working to roll back this change.

We have completed the rollback and are now seeing a reduction of 502 errors. We will continue to monitor traffic to ensure that error rates continue to return to the normal range.

We have continued to see good performance after the rollback and are now marking this issue as resolved.

We are experiencing an issue affecting asynchronous transcription requests using Universal-3 Pro on our EU endpoint. Beginning at 15:05 UTC, requests have increased processing time and some are resulting in errors. Our team is working to restore normal processing. Our US endpoint is not affected. Our team is actively investigating this issue.

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

A fix has been implemented. We are seeing processing times return to the normal ranges and are continuing to monitor the results.

This incident has been resolved. Between approximately 15:05 and 15:45 UTC, async transcription requests using Universal-3 Pro on our EU endpoint took longer than usual to complete, and some requests failed. Processing times have returned to normal ranges and any requests that failed during this window can be safely resubmitted.

We have identified an issue affecting asynchronous transcription requests using Universal-3.5 Pro on our US endpoint. Beginning at 1:35p UTC, requests have increased processing time and some are resulting in errors. Our team is working to restore normal processing. Our EU endpoint is not affected. We will continue to provide updates as more information becomes available.

We have identified the issue and a fix has been released. We will provide further updates as soon as we can.

A fix has been implemented. We are seeing processing times return to the normal ranges and are continuing to monitor the results.

This incident has been resolved. Between approximately 1:35p and 2:20p UTC, async transcription requests using Universal-3.5 Pro on our US endpoint took longer than usual to complete, and some requests failed. Processing times have returned to normal ranges and any requests that failed during this window can be safely resubmitted.

From 10:30a - 12:30a UTC users experienced rejected connections when connecting to our Realtime Universal-3.6 Pro model on our US endpoint. Users received a 3005 Session Cancelled error message on connection. This issue has been resolved and the Realtime US endpoint for Universal-3.6 Pro is functioning normally. The EU Realtime endpoint was not affected.