Live / AssemblyAI / Incident
AssemblyAI: Increased Processing Times and Errors on US Endpoint for Universal-3.5 Pro Async model
AssemblyAI · assemblyai.comMajor incidentResolved2026-10-06 14:25 UTC
Public — what happened
Summary
AssemblyAI reported a major issue in which asynchronous transcription jobs sent to its US endpoint with the Universal-3.5 Pro model were taking longer than usual to process, with some failing outright. The company said the slowdown began at 1:35 p.m. UTC on October 6, 2026, and that its EU endpoint was unaffected. AssemblyAI said it found the problem and released a fix, though it did not describe the cause, after which processing times went back to normal. The incident was marked resolved at 14:25 UTC the same day.
Affected
Asynchronous API
Timeline
- Started — 2026-10-06 14:00 UTC
- Investigating — 2026-10-06 14:00 UTC
- Identified — 2026-10-06 14:10 UTC
- Monitoring — 2026-10-06 14:13 UTC
- Resolved — 2026-10-06 14:25 UTC · 25 min after it started
With SquidGrid — where it starts on the route
Independent path health
The status page is the symptom. SquidGrid measures the paths that reach AssemblyAI against their own baselines — whether the routes carrying your traffic degraded, at which handoff, and who owns that stretch.
🔒 Sign in to seeCustomers get the live Provider Assessment Report for AssemblyAI: its full incident track record, what tends to break, and recent public reports of problems.
Included with any paid plan.
Open the AssemblyAI report →
More from AssemblyAI
Covered in The Squid’s Ink, Week 42, 2026, our weekly internet health report.