We started checking AssemblyAI on November 2, 2026, which is 7 days ago. Everything below covers that period, not the full 90 days a longer-tracked service would show.
Email me when AssemblyAI reports an incident on its status page, and again when it reports it resolved.
01
The last 24 hours
What happened most recently, on one time axis: our own probe readings by surface, how many people reported a problem, and what AssemblyAI's own status page declared. Below it, any public chatter we saw about AssemblyAI and the extra probe it triggered.
The last 24 hours on one axis: what our probes read for each surface we check, how many people reported a problem, and what AssemblyAI's own status page declared. Three records side by side; none of them changes another.
Our probes, web
Our probes, api (primary)
Unverified user reportsNo reports about AssemblyAI in the last 24 hours, which is not evidence that nothing is wrong.
AssemblyAI's status pageNo incident declared in the last 24 hours.
24h ago18h ago12h ago6h agonow
Each check cell is the worst reading across every region in that quarter hour: one region that did not answer colours the cell, never an average. An amber cell is a reading that answered, but at three times or more its 7-day median for three checks running: slow is not down, and we say which. A filtered reading stays neutral, because a refused check is not a failed check. Report bars count reports as submitted; we do not check who sent them, and they never change our reading. The status-page lane is AssemblyAI's own declaration, shown as they made it.
Third-party chatter, labeled
Public posts from the last hour that mention AssemblyAI next to an outage word (“down”, “outage”, “not working”). This is what other people said in public, collected by keyword: not something we measured, and not the user reports above. It never affects the verdict.
No matching public posts in the last hour from the sources we watch.
Confirmation probe23:36 UTC, Asia-Pacific: their own status feed changing prompted an extra probe. Result: AssemblyAI answered normally.
Confirmation probe23:36 UTC, Europe: their own status feed changing prompted an extra probe. Result: AssemblyAI answered normally.
Confirmation probe23:34 UTC, US-East: their own status feed changing prompted an extra probe. Result: AssemblyAI answered normally.
Confirmation probe23:34 UTC, US-West: their own status feed changing prompted an extra probe. Result: AssemblyAI answered normally.
02
Checks passing by region
Checks passing is the checks that passed, divided by every check we attempted, per region. Not interpolated, not smoothed, and never computed for a region with zero recorded samples.
Region
Checks passing
Probes recorded
US-East
100.00%
734
US-West
100.00%
592
Europe
100.00%
541
Asia-Pacific
100.00%
327
Their declared record
AssemblyAI's own incident history, taken from their public status feed. This is their account of what happened, not our check reading.
Elevated errors and delays for Universal-3 Pro, Universal-3.5 Pro and Universal-3.6 ProMinor incident
Nov 2, 2026, 9:42 PM UTC to Nov 2, 2026, 10:58 PM UTC (1h 16m)resolved
their latest update (Nov 2, 2026, 10:58 PM UTC): We have continued to see good performance after the rollback, and error rates and processing times have remained in the normal ranges. We are now marking this issue as resolved. Any requests that returned an error during this incident can be safely resubmitted.
Real-time STT: 502 errors related to change to temporary tokensMinor incident
Oct 28, 2026, 6:11 PM UTC to Oct 28, 2026, 6:53 PM UTC (42 min)resolved
their latest update (Oct 28, 2026, 6:53 PM UTC): We have continued to see good performance after the rollback and are now marking this issue as resolved.
Increased Processing Times and Errors on EU Endpoint for Universal-3 Pro Async modelMinor incident
Oct 6, 2026, 3:44 PM UTC to Oct 6, 2026, 4:03 PM UTC (19 min)resolved
their latest update (Oct 6, 2026, 4:03 PM UTC): This incident has been resolved. Between approximately 15:05 and 15:45 UTC, async transcription requests using Universal-3 Pro on our EU endpoint took longer than usual to complete, and some requests failed. Processing times have returned to normal ranges and any requests that fa…
Increased Processing Times and Errors on US Endpoint for Universal-3.5 Pro Async modelPartial outage
Oct 6, 2026, 2:00 PM UTC to Oct 6, 2026, 2:25 PM UTC (25 min)resolved
their latest update (Oct 6, 2026, 2:25 PM UTC): This incident has been resolved. Between approximately 1:35p and 2:20p UTC, async transcription requests using Universal-3.5 Pro on our US endpoint took longer than usual to complete, and some requests failed. Processing times have returned to normal ranges and any requests that …
Rejected Sessions on US Endpoint for Universal-3.6 Pro Realtime ModelMinor incident
Oct 6, 2026, 10:30 AM UTC to Oct 6, 2026, 10:30 AM UTC (0 min)resolved
their latest update (Oct 6, 2026, 10:30 AM UTC): From 10:30a - 12:30a UTC users experienced rejected connections when connecting to our Realtime Universal-3.6 Pro model on our US endpoint. Users received a 3005 Session Cancelled error message on connection. This issue has been resolved and the Realtime US endpoint for Universal…
Increased processing times and errors for Universal-3.5 Pro on the EU async endpointPartial outage
Oct 5, 2026, 10:21 AM UTC to Oct 5, 2026, 11:39 AM UTC (1h 18m)resolved
their latest update (Oct 5, 2026, 11:39 AM UTC): This incident has been resolved. Between approximately 08:20 and 10:45 UTC, asynchronous transcription requests using Universal-3 Pro and Universal-3.5 Pro on our EU endpoint took longer than usual to complete, and some requests failed. Processing times have returned to normal ra…
Increased turnaround times for Async Universal-3 modelMinor incident
Sep 28, 2026, 5:27 PM UTC to Sep 28, 2026, 5:58 PM UTC (31 min)resolved
their latest update (Sep 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.
Outage on US Async EndpointMajor outage
Sep 16, 2026, 8:22 PM UTC to Sep 16, 2026, 9:37 PM UTC (1h 15m)postmortem published
their latest update (Sep 21, 2026, 8:38 PM UTC): **Summary**
On September 16, 2026, between 20:04 and 21:08 UTC, our US Async API returned elevated server errors. At peak, roughly 50% of async transcription requests on the US endpoint failed, and a portion of the requests that did succeed took longer than usual to complete. Ou…
Elevated turnaround times for async transcriptionAll systems operational
Sep 13, 2026, 11:30 PM UTC to Sep 13, 2026, 11:30 PM UTC (0 min)resolved
their latest update (Sep 13, 2026, 11:30 PM UTC): Resolved: Between 23:30 and 23:37 UTC on September 13, 2026, async transcription requests experienced elevated turnaround times due to an unexpected spike in processing load. We scaled out additional capacity and turnaround times returned to normal levels. Requests submitted duri…
Increased latency for Universal 3.5 Pro Realtime modelMinor incident
Aug 25, 2026, 2:55 PM UTC to Aug 25, 2026, 3:01 PM UTC (6 min)resolved
their latest update (Aug 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.
Showing the 10 most recent of 51 incidents AssemblyAI has declared in the history we hold.
These entries are AssemblyAI's own declarations, taken from their public status feed, shown separately from our own check readings. Their page publishes what they choose to publish: an incident missing here means they did not declare one, not that nothing happened, and an incident here is their account, not our measurement. Neither record ever changes the other.
AssemblyAI's own status feed works, so its declared incidents are the record and our probe events are not listed or counted. Our check results by region are above, as a reading beside the statement.
Full detail on what a probe does and does not prove is in the methodology page.