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.
Posted Nov 02, 2026 - 22:58 UTC
Monitoring
Error rates and processing times have returned to normal. We're monitoring to make sure performance remains stable.
Posted Nov 02, 2026 - 22:44 UTC
Update
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.
Posted Nov 02, 2026 - 22:42 UTC
Update
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.
Posted Nov 02, 2026 - 22:08 UTC
Identified
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.