AssemblyAI Outage History

40 incidents recorded over the last 365 days, 38 of them resolved. Durations are measured from when PulsAPI first saw the problem to when it cleared, which is usually longer than the vendor's own figure.

Live AssemblyAI status99.75% uptime history

Every Recorded AssemblyAI Incident

AssemblyAI incidents, newest first, with date, duration and status.
DateIncidentDurationStatus
Aug 20, 2026Async Transcription Service IssuesThis incident has been resolved. Between approximately 13:40 and 14:40 UTC, asynchronous transcription requests on our US endpoint experienced elevated latency and errors. Processing times and error rates have returned…49 minResolved
Aug 19, 2026EU endpoint session failures on Universal 3.5 Pro RealtimeThis incident has been resolved. From 13:00–13:12 UTC, users creating new streaming sessions using the EU endpoint were receiving a 3005 close code.7 minResolved
Aug 18, 2026Elevated processing times for Universal-3 Pro and Universal-3.5 Pro async transcriptionThis incident has been resolved. Processing times for pre-recorded transcription requests using Universal-3 Pro and Universal-3.5 Pro have returned to normal ranges and the backlog has cleared.38 minResolved
Aug 14, 2026Delayed Webhook Delivery on Async EU EndpointThis incident has been resolved. The affected webhook events remained queued and were delivered after service recovered; no events were lost. The queue is now clear, and no customer action is required.20 minResolved
Aug 3, 2026503 Error when using temp tokens with Realtime APIThis incident has been resolved.1h 47mResolved
Aug 1, 2026Degraded Universal-3.5 Pro streaming in us-eastThis incident affected a subset of Universal-3.5 Pro streaming sessions in the us-east region on July 31 between 20:15 and 22:15 UTC. Affected sessions connected successfully but did not process incoming audio, so no…-1257 minResolved
Jul 16, 2026Degraded streaming session creation for Universal Streaming English in us-westThis incident affected newly created Universal Streaming English sessions in the us-west region on July 7 between 15:00 and 15:10 UTC. Affected sessions were cancelled with error code 3005 shortly after connecting and…-13485 minResolved
Jul 9, 2026Increased processing times for US async transcriptionThis incident has been resolved. Async transcription processing times on the US endpoint have returned to normal ranges and webhook deliveries are operating normally.19 minResolved
Jun 25, 2026Timeout on transcriptions using speaker labels**What happened** An issue related to our speaker diarization service caused certain requests to hang until they timed out. This lead to a backlog of requests to our async API creating a processing queue across our US…1h 10mResolved
Jun 24, 2026Pre-recorded Universal-3-pro and Universal-3-5-pro degradation in the EUThe issue affecting EU pre-recorded transcription for Universal-3-Pro and Universal-3-5-Pro has been fully resolved, the fix was implemented at 10:05 UTC. All systems are operating normally. We apologize for the…1h 26mResolved
May 27, 2026Degraded New Account Signup and Account ProvisioningProcesses are continuing to work normally, and all affected accounts have been fixed, so we are not moving this issue to resolved.1h 13mResolved
May 19, 2026Increased processing times and errors for Async EU endpointThis incident is resolved. To summarize, this incident began at 9am UTC and a fix was implemented around 10am UTC. This incident affected async requests to our EU endpoint and resulted in an increase in processing time…4h 20mResolved
May 7, 2026Billing Balance & Notification DelaysThis incident has been resolved.3h 8mResolved
Apr 16, 2026Increased processing times and errors for Universal-2We have continued to see processing times remain in the normal range and are now marking this issue as resolved.47 minResolved
Apr 9, 2026Degraded Async Transcription PerformanceThe issue affecting async transcription processing has been fully resolved. All systems are operating normally. We apologize for the disruption to your workflows. If you have any questions, please reach out to…15 minResolved
Apr 6, 2026Pre-recorded STT requests that include Content Moderation failingResolved – Content Safety Errors | April 6, 2026 Incident Window: 18:14 – 20:06 UTC Current Status: Resolved ✅ On April 6, 2026, during the incident window, customers using our Content Safety feature for Pre-recorded…0 minResolved
Mar 30, 2026Increase in error rates for Claude Sonnet 4.6The AWS Bedrock issues have been resolved, and we have once again seen success rates for Claude models, including Sonnet 4.6, return to normal levels.5h 13mResolved
Mar 6, 2026Longer than usual processing times for transcription of pre-recorded audioFrom approximately 10:10am to 10:28am PT we experienced longer-than-usual processing times for transcription of pre-recorded audio. The root cause of this slowdown has been identified and resolved, and response times…0 minResolved
Feb 28, 2026Billing Issue Affecting Some Universal-3-Pro UsersThe billing issue that caused unexpected multiple auto-refill charges for a subset of Universal-3-Pro customers on February 28, 2025, has been resolved. Refunds have been issued to the affected customers.1h 24mResolved
Feb 27, 2026Degraded Speaker Identification and TranslationThis incident has been resolved.1h 52mResolved
Feb 25, 2026Negative Balance ErrorThe negative balance error affecting a small number of accounts has been resolved. This issue was an unintentional error that occurred as a result of our ongoing billing system migration. Our team is continuing to…1h 55mResolved
Feb 9, 2026Increase in 429 errors with LLM Gateway requests using Haiku 4.5This issue has been resolved and LLM Gateway requests using Haiku 4.5 are continuing to complete normally.4h 39mResolved
Jan 29, 2026Async + LLM gateway APIs returning 5xx**Summary: January 29 Outage** On January 29, our Async Transcription and LLM Gateway went down for 25 minutes, followed by two hours of degraded performance. Here's what happened. Our traffic has been steadily…1h 38mResolved
Jan 28, 2026Higher latency when using the EU endpointWe have continued to see good performance, and traffic is once again working normally so we are marking this issue as resolved.2h 7mResolved
Jan 11, 2026Streaming API: Infrastructure MaintenanceScheduled maintenance has been completed and everything is working normally.3h 0mScheduled
Jan 5, 2026Elevated connection errors when starting new Streaming sessionsThis increase in errors was inadvertantly caused by a change that was made around 8:30am PT, which was immediately reverted when our team noticed the increase in errors. We have continued to see good performance since…17 minResolved
Nov 24, 2025Expected responses from LLM Gateway using Claude modelsWe have continued to see good performance since releasing the earlier fix and are now marking this issue as resolved.3h 5mResolved
Nov 20, 2025Delayed processing of transcripts on SlamThis incident has been resolved.1h 20mResolved
Nov 18, 2025Cloudflare outage affecting documentation access and Google Auth flow on dashboardCloudflare has restored normal operation, and access to our documentation and Google Authentication is fully restored. All services are functioning as expected, and the incident is now resolved.6h 43mResolved
Nov 15, 2025SSL certificate validation errors connecting to Streaming APIFrom 8p GMT on November 14, 2025 - 2:20p GMT on November 15, 2025, users connecting to our Streaming API using our US endpoint `wss://streaming.assemblyai.com/v3/ws` from Europe, Africa, and eastern Asia were…0 minResolved
Nov 1, 2025Streaming API: Infrastructure MaintenanceThe scheduled infrastructure maintenance for our Streaming STT service has been successfully completed. All services are operating normally. Thank you for your patience as we worked to improve our infrastructure.12h 0mScheduled
Oct 31, 2025Degraded performance for requests using Slam-1This incident has been resolved.2h 49mResolved
Oct 30, 2025Degraded performance for requests using Slam-1We have continued to see good performance and success rates for Slam-1 and are now marking this issue as resolved.6h 44mResolved
Oct 22, 2025Requests failing for Slam-1 modelWe have continued to see good performance for requests using Slam-1 and are now marking this issue as resolved.6h 1mResolved
Oct 20, 2025Account Creation IssuesThis incident has been resolved.1h 29mResolved
Sep 30, 2025Increased error rates for pre-recorded Speech-to-TextWe have continued to see good performance for pre-recorded audio so we are now marking this issue as resolved.2h 54mResolved
Sep 29, 2025Some Streaming Sessions are Failing to be EstablishedWe have continued to see good performance since rolling back the update that was identified to be the cause of this issue, so we are marking this issue as resolved.11h 41mResolved
Sep 23, 2025Increased Processing Time for Non-English Language TranscriptionsFrom 8a - 10a GMT there was an issue related to the pick-up time of our non-English language models. This caused an increase in processing time for pre-recorded transcriptions. Our Engineering team has released a fix…0 minResolved
Sep 22, 2025Increase in turnaround times for pre-recorded audio transcriptionAside from a small window of about five minutes around 12:10pm PT where turnaround times were slightly higher than usual, we have continued to see turnaround times within the expected ranges so we are now closing this…14 minResolved
Sep 16, 2025Degraded Streaming PerformanceWe experienced an issue with our Streaming API between 09:00 GMT and 10:04 GMT. This resulted in reduced quality of service for streaming sessions and some sessions were closing unexpectedly. A fix was implemented and…-90 minResolved

How to Read This AssemblyAI Incident Log

Each row is an incident PulsAPI observed, not a summary written afterwards. The duration is wall-clock time between the first failing check and the first clean one, so it includes the window before AssemblyAI acknowledged anything. Vendor post-mortems typically measure from acknowledgement, which is why their numbers are usually shorter.

Incidents still open have no duration yet and are listed as ongoing rather than being given a running total. The archive covers the last 365 days; anything older has aged out of the window rather than never having happened.

The longest single AssemblyAI outage in this window ran 12h, against a mean recovery of 2h 32m. If you depend on AssemblyAI in a customer-facing path, the longest figure is the one to design around. The mean is what happens on a normal bad day; the maximum is what happens on the worst one.