Increased turnaround times for Async Universal-3 model

What to do

• Check whether you use AssemblyAI Asynchronous API. Check your stack

  Paste a package.json, lockfile, Terraform or a list of domains at down.guide/stack to see every provider you depend on.

• Confirm your retries, queues and scheduled jobs caught up after the 31m it lasted.

  Anything that failed between 2026-09-28 17:27 UTC and 2026-09-28 17:58 UTC may need a replay.

• Subscribe to AssemblyAI's feed to hear about the next one first. RSS feed

  https://down.guide/feed?provider=assemblyai works in Slack (/feed subscribe), Discord feed bots and any RSS reader.

Updates from AssemblyAI 4

1. identifiedSep 28, 2026, 5:27 PM UTC

   We are currently experiencing issues that are resulting in longer-than-usual processing times for Async STT requests using our Universal-3 models. We are working to resolve this issue as quickly as possible and will provide further updates as soon as we can.

   provider

2. identifiedSep 28, 2026, 5:38 PM UTC

   We are still working to fully resolve the issue, but we are seeing improvement in turnaround times for the Universal-3 Pro models.

   provider

3. monitoringSep 28, 2026, 5:44 PM UTC

   We have continued to work to resolve this issue and are now seeing processing times return to the normal ranges, but we are continuing to monitor to ensure good performance.

   provider

4. resolvedSep 28, 2026, 5:58 PM UTC

   Processing times have continued to be in the normal range, so we are now marking this issue as resolved.

   provider

Corrections

None so far.

Something wrong on this page? Report an error or send us a note. Every fix is listed here.