AssemblyAI outage history

Biggest AssemblyAI outages

Ranked by the official impact level, then by how long they lasted. Each has its own page with the cause, the fix time and every official update.

1. Jan 29, 2026: Async + LLM gateway APIs returning 5xx 1 hour 38 min · rated "Critical"
2. Jun 24, 2026: Pre-recorded Universal-3-pro and Universal-3-5-pro degradation in the EU 1 hour 26 min · rated "Critical"
3. Sep 16, 2026: Outage on US Async Endpoint 1 hour 15 min · rated "Critical"
4. Nov 18, 2025: Cloudflare outage affecting documentation access and Google Auth flow on dashboard 6 hours 43 min · rated "Major"
5. Oct 22, 2025: Requests failing for Slam-1 model 6 hours 1 min · rated "Major"

Every smaller AssemblyAI incident

Minor and short incidents from the AssemblyAI status page, newest first, each with a line from the official updates. Times are UTC.

October 2026

• Oct 6, 2026, 15:44 UTC · Increased Processing Times and Errors on EU Endpoint for Universal-3 Pro Async model

  19 minutes · rated "Minor"

  "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."

• Oct 6, 2026, 14:00 UTC · Increased Processing Times and Errors on US Endpoint for Universal-3.5 Pro Async model

  25 minutes · rated "Major"

  "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."

• Oct 6, 2026, 10:30 UTC · Rejected Sessions on US Endpoint for Universal-3.6 Pro Realtime Model

  duration not stated · rated "Minor"

  "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."

• Oct 5, 2026, 10:21 UTC · Increased processing times and errors for Universal-3.5 Pro on the EU async endpoint

  1 hour 18 min · rated "Major"

  "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."

September 2026

• Sep 28, 2026, 17:27 UTC · Increased turnaround times for Async Universal-3 model

  31 minutes · rated "Minor"

  "Processing times have continued to be in the normal range, so we are now marking this issue as resolved."

• Sep 14, 2026, 01:27 UTC · Elevated turnaround times for async transcription

  duration not stated · marked as no impact

  "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."

August 2026

• Aug 25, 2026, 14:55 UTC · Increased latency for Universal 3.5 Pro Realtime model

  6 minutes · rated "Minor"

  "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."

• Aug 20, 2026, 14:21 UTC · Async Transcription Service Issues

  49 minutes · rated "Minor"

  "This incident has been resolved. Between approximately 13:40 and 14:40 UTC, asynchronous transcription requests on our US endpoint experienced elevated latency and errors."

• Aug 19, 2026, 13:17 UTC · EU endpoint session failures on Universal 3.5 Pro Realtime

  7 minutes · rated "Major"

  "This 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."

• Aug 18, 2026, 19:34 UTC · Elevated processing times for Universal-3 Pro and Universal-3.5 Pro async transcription

  38 minutes · rated "Minor"

  "This 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."

• Aug 14, 2026, 14:49 UTC · Delayed Webhook Delivery on Async EU Endpoint

  20 minutes · rated "Minor"

  "This 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."

• Aug 3, 2026, 16:08 UTC · 503 Error when using temp tokens with Realtime API

  1 hour 48 min · rated "Minor"

  "We are continuing to work on a fix for the issue. The API is stable and the errors subsided at 5:11pm UTC."

• Aug 1, 2026, 16:57 UTC · Degraded Universal-3.5 Pro streaming in us-east

  duration not stated · marked as no impact

  "This 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."

July 2026

• Jul 9, 2026, 13:53 UTC · Increased processing times for US async transcription

  19 minutes · rated "Minor"

  "This incident has been resolved. Async transcription processing times on the US endpoint have returned to normal ranges and webhook deliveries are operating normally."

• Jul 7, 2026, 15:00 UTC · Degraded streaming session creation for Universal Streaming English in us-west

  duration not stated · marked as no impact

  "This incident affected newly created Universal Streaming English sessions in the us-west region on July 7 between 15:00 and 15:10 UTC."

June 2026

• Jun 25, 2026, 15:37 UTC · Timeout on transcriptions using speaker labels

  1 hour 11 min · rated "Major"

  "The issue has been identified and a fix has been released."

May 2026

• May 27, 2026, 21:00 UTC · Degraded New Account Signup and Account Provisioning

  1 hour 14 min · rated "Minor"

  "Processes are continuing to work normally, and all affected accounts have been fixed, so we are not moving this issue to resolved."

• May 19, 2026, 11:08 UTC · Increased processing times and errors for Async EU endpoint

  4 hours 21 min · rated "Minor"

  "This 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 and errors."

• May 7, 2026, 13:56 UTC · Billing Balance & Notification Delays

  3 hours 8 min · rated "Minor"

  "The issue has been identified and a fix is being implemented."

April 2026

• Apr 16, 2026, 18:37 UTC · Increased processing times and errors for Universal-2

  47 minutes · rated "Minor"

  "We have continued to see processing times remain in the normal range and are now marking this issue as resolved."

• Apr 9, 2026, 21:33 UTC · Degraded Async Transcription Performance

  15 minutes · rated "Major"

  "The 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 support@assemblyai.com."

• Apr 6, 2026, 21:51 UTC · Pre-recorded STT requests that include Content Moderation failing

  duration not stated · marked as no impact

  "Resolved - 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 STT experienced..."

March 2026

• Mar 30, 2026, 18:41 UTC · Increase in error rates for Claude Sonnet 4.6

  5 hours 14 min · rated "Minor"

  "The 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."

• Mar 6, 2026, 19:04 UTC · Longer than usual processing times for transcription of pre-recorded audio

  duration not stated · rated "Minor"

  "From approximately 10:10am to 10:28am PT we experienced longer-than-usual processing times for transcription of pre-recorded audio."

February 2026

• Feb 28, 2026, 19:19 UTC · Billing Issue Affecting Some Universal-3-Pro Users

  1 hour 25 min · rated "Minor"

  "The 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."

• Feb 27, 2026, 13:29 UTC · Degraded Speaker Identification and Translation

  1 hour 52 min · rated "Minor"

  "The issue has been identified and a fix is being implemented."

• Feb 25, 2026, 19:39 UTC · Negative Balance Error

  1 hour 55 min · rated "Major"

  "The 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."

• Feb 9, 2026, 19:53 UTC · Increase in 429 errors with LLM Gateway requests using Haiku 4.5

  4 hours 40 min · rated "Minor"

  "This issue has been resolved and LLM Gateway requests using Haiku 4.5 are continuing to complete normally."

January 2026

• Jan 28, 2026, 17:50 UTC · Higher latency when using the EU endpoint

  2 hours 8 min · rated "Minor"

  "We have continued to see good performance, and traffic is once again working normally so we are marking this issue as resolved."

• Jan 5, 2026, 16:45 UTC · Elevated connection errors when starting new Streaming sessions

  18 minutes · rated "Minor"

  "This 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."

November 2025

• Nov 24, 2025, 22:39 UTC · Expected responses from LLM Gateway using Claude models

  3 hours 6 min · rated "Minor"

  "We have continued to see good performance since releasing the earlier fix and are now marking this issue as resolved."

• Nov 20, 2025, 08:21 UTC · Delayed processing of transcripts on Slam

  1 hour 20 min · rated "Major"

  "The issue has been identified and a fix is being implemented."

• Nov 15, 2025, 14:30 UTC · SSL certificate validation errors connecting to Streaming API

  duration not stated · rated "Minor"

  "From 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."

October 2025

• Oct 31, 2025, 10:38 UTC · Degraded performance for requests using Slam-1

  2 hours 49 min · rated "Minor"

  "The issue has been identified and a fix is being implemented."

• Oct 30, 2025, 19:36 UTC · Degraded performance for requests using Slam-1

  6 hours 45 min · rated "Minor"

  "We have continued to see good performance and success rates for Slam-1 and are now marking this issue as resolved."

• Oct 20, 2025, 23:00 UTC · Account Creation Issues

  1 hour 30 min · rated "Minor"

  "We are currently experiencing an issue with new account creation due to the ongoing AWS issues that may affect the ability of newly created accounts to use our API or Playground."