Live / AssemblyAI / Incident
AssemblyAI: Elevated errors and delays for Universal-3 Pro, Universal-3.5 Pro and Universal-3.6 Pro
AssemblyAI · assemblyai.comMinor incidentResolved2026-11-02 22:58 UTC
Public — what happened
Summary
AssemblyAI said that starting at 21:42 UTC on 2026-11-02, a large share of its pre-recorded transcription requests using the Universal-3.5 Pro and Universal-3.6 Pro models either failed or took longer than normal, in all regions. The company said live streaming transcription was not affected. AssemblyAI said it had identified the cause as a recent change and began undoing it, and by 22:08 UTC it reported error rates falling while some requests could still fail or run slowly. The incident is marked resolved as of 22:58 UTC, and the company classed it as minor.
Affected
Asynchronous API
Timeline
- Started — 2026-11-02 21:42 UTC
- Identified — 2026-11-02 21:42 UTC (2 updates)
- Resolved — 2026-11-02 22:58 UTC · 1h 16m 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 46, 2026, our weekly internet health report.