Increased latency for Universal 3.5 Pro Realtime model

What to do

• Check whether you use AssemblyAI Streaming API in eu, us. 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 6m it lasted.

  Anything that failed between 2026-08-25 14:55 UTC and 2026-08-25 15:01 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. investigatingAug 25, 2026, 2:55 PM UTC

   We are currently investigating an issue where there is increased latency for our Universal 3.5 Pro Realtime model on the US endpoint. This began at 14:15 UTC.

   provider

2. identifiedAug 25, 2026, 2:57 PM UTC

   The issue has been identified and our team is working on a fix.

   provider

3. monitoringAug 25, 2026, 2:57 PM UTC

   The fix has been implemented and latency has recovered as of 14:45 UTC. The team is continuing to monitor the situation.

   provider

4. resolvedAug 25, 2026, 3:01 PM UTC

   This incident has been resolved. From 14:15-14:45 UTC customers experienced increased latency when using our Universal 3.5 Pro Realtime model on the US endpoint. The EU endpoint was not affected. Sessions continued to function during this time without any errors.

   provider

Corrections

None so far.

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