AssemblyAI Incident History

This incident affected newly created Universal Streaming English sessions in the us-west region on July 7 between 15:00 and 15:10 UTC. Affected sessions were cancelled with error code 3005 shortly after connecting and did not return transcripts. Sessions already in progress, other regions, and other streaming models were unaffected. Service returned to normal at 15:10 UTC. We apologize for the disruption to your workflows. If you have any questions, please reach out to support@assemblyai.com.

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

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.

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

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

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.

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