AssemblyAI

Affected: Asynchronous API

Failure mode: The text does not say enough to tell. Root cause: The vendor does not say why it happened. Tagged by claude-haiku-5-5 with medium confidence (taxonomy v0.2).

1. investigating 2026-10-06 15:44 UTC

   We are experiencing an issue affecting asynchronous transcription requests using Universal-3 Pro on our EU endpoint. Beginning at 15:05 UTC, requests have increased processing time and some are resulting in errors. Our team is working to restore normal processing. Our US...

2. identified 2026-10-06 15:44 UTC

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

3. monitoring 2026-10-06 15:46 UTC

   A fix has been implemented. We are seeing processing times return to the normal ranges and are continuing to monitor the results.

4. resolved 2026-10-06 16:03 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...

Excerpts are shortened. Read the full incident on AssemblyAI's status page.

Affected: Asynchronous API

Failure mode: A code release introduced the failure. Root cause: A bug in the vendor's own code. Tagged by claude-haiku-5-5 with medium confidence (taxonomy v0.2).

1. investigating 2026-10-06 14:00 UTC

   We have identified an issue affecting asynchronous transcription requests using Universal-3.5 Pro on our US endpoint. Beginning at 1:35p UTC, requests have increased processing time and some are resulting in errors. Our team is working to restore normal processing. Our EU...

2. identified 2026-10-06 14:10 UTC

   We have identified the issue and a fix has been released. We will provide further updates as soon as we can.

3. monitoring 2026-10-06 14:13 UTC

   A fix has been implemented. We are seeing processing times return to the normal ranges and are continuing to monitor the results.

4. resolved 2026-10-06 14:25 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...

Excerpts are shortened. Read the full incident on AssemblyAI's status page.

Failure mode: Orchestration, control plane, service discovery or load balancing failed. Root cause: The vendor does not say why it happened. Tagged by claude-haiku-5-5 with low confidence (taxonomy v0.2).

1. resolved 2026-10-06 10:30 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...

Excerpts are shortened. Read the full incident on AssemblyAI's status page.

Affected: Asynchronous API

Failure mode: The text does not say enough to tell. Root cause: The vendor does not say why it happened. Tagged by claude-haiku-5-5 with medium confidence (taxonomy v0.2).

1. investigating 2026-10-05 10:21 UTC

   We have identified an issue affecting asynchronous transcription requests using Universal-3.5 Pro on our EU endpoint. Most of these requests are currently significantly delayed, and some have failed. Our team is working to restore normal processing. Our US endpoint and real-time...

2. identified 2026-10-05 10:38 UTC

   We have identified the issue causing longer-than-usual processing times and some failed requests for asynchronous transcription using our Universal-3 Pro and Universal-3.5 Pro models on the EU endpoint. We are working to resolve this as quickly as possible and will provide...

3. monitoring 2026-10-05 10:43 UTC

   We have continued to work to resolve this issue and are now seeing processing times return to the normal ranges, but we are continuing to monitor to ensure good performance.

4. resolved 2026-10-05 11:39 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...

Excerpts are shortened. Read the full incident on AssemblyAI's status page.

Affected: Asynchronous API

Failure mode: Exhausted memory, disk, CPU, queues, connection pools or quotas. Root cause: The vendor does not say why it happened. Tagged by claude-haiku-5-5 with low confidence (taxonomy v0.2).

1. identified 2026-09-28 17:27 UTC

   We are currently experiencing issues that are resulting in longer-than-usual processing times for Async STT requests using our Universal-3 models. We are working to resolve this issue as quickly as possible and will provide further updates as soon as we can.

2. identified 2026-09-28 17:38 UTC

   We are still working to fully resolve the issue, but we are seeing improvement in turnaround times for the Universal-3 Pro models.

3. monitoring 2026-09-28 17:44 UTC

   We have continued to work to resolve this issue and are now seeing processing times return to the normal ranges, but we are continuing to monitor to ensure good performance.

4. resolved 2026-09-28 17:58 UTC

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

Excerpts are shortened. Read the full incident on AssemblyAI's status page.

Affected: Asynchronous API

Failure mode: A provider or third-party service this vendor depends on failed. Root cause: A failure at a provider or vendor they depend on. Tagged by claude-haiku-5-5 with high confidence (taxonomy v0.2).

Names an upstream provider: AWS.

1. investigating 2026-09-16 20:22 UTC

   We are currently investigating an issue that is affecting all customers using our Async API on our US endpoint. Users will be receiving a server error. We will update with more information as we learn more. This began at 8pm UTC.

2. identified 2026-09-16 20:24 UTC

   The issue has been identified. This is affecting approximately 50% of all async transcriptions on the US endpoint.

3. identified 2026-09-16 20:57 UTC

   We are continuing to investigate these elevated errors. We will provide an update as soon as possible.

4. identified 2026-09-16 21:10 UTC

   We are seeing a reduction in the number of errors, but we are still working to fully resolve the issue.

5. monitoring 2026-09-16 21:12 UTC

   We have mitigated the issue and our Async API service is recovering.

6. resolved 2026-09-16 21:37 UTC

   The issue, which was the result of an AWS service issue, has been resolved and we have continue to see good performance since implementing a fix so we are now closing this issue.

7. postmortem 2026-09-21 20:38 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....

Excerpts are shortened. Read the full incident on AssemblyAI's status page.

Failure mode: Traffic surge or denial-of-service attack. Root cause: The vendor does not say why it happened. Tagged by claude-haiku-5-5 with medium confidence (taxonomy v0.2).

1. resolved 2026-09-13 23:30 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...

Excerpts are shortened. Read the full incident on AssemblyAI's status page.

Affected: Streaming API

Failure mode: The text does not say enough to tell. Root cause: The vendor does not say why it happened. Tagged by claude-haiku-5-5 with medium confidence (taxonomy v0.2).

1. investigating 2026-08-25 14:55 UTC

   We are currently investigating an issue where there is increased latency for our Universal 3.5 Pro Realtime model on the US endpoint. This began at 14:15 UTC.

2. identified 2026-08-25 14:57 UTC

   The issue has been identified and our team is working on a fix.

3. monitoring 2026-08-25 14:57 UTC

   The fix has been implemented and latency has recovered as of 14:45 UTC. The team is continuing to monitor the situation.

4. resolved 2026-08-25 15:01 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.

Excerpts are shortened. Read the full incident on AssemblyAI's status page.

Affected: Asynchronous API

Failure mode: Exhausted memory, disk, CPU, queues, connection pools or quotas. Root cause: Not enough capacity for the load. Tagged by claude-haiku-5-5 with medium confidence (taxonomy v0.2).

1. investigating 2026-08-20 14:21 UTC

   We’re seeing elevated latency and errors on async transcription submissions, and our on-call team is actively investigating. Capacity is scaling out now, and we’re monitoring recovery.

2. identified 2026-08-20 14:25 UTC

   We have identified the cause of the elevated error rates affecting asynchronous transcription requests. Our engineering team is actively restoring capacity, and error rates should improve as this completes. We will continue to provide updates as more information becomes...

3. monitoring 2026-08-20 14:39 UTC

   A fix has been implemented and we are monitoring recovery.

4. resolved 2026-08-20 15:10 UTC

   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. Processing times and error rates have returned to normal ranges and the backlog has cleared.

Excerpts are shortened. Read the full incident on AssemblyAI's status page.

Affected: Streaming API

Failure mode: The text does not say enough to tell. Root cause: The vendor does not say why it happened. Tagged by claude-haiku-5-5 with low confidence (taxonomy v0.2).

1. investigating 2026-08-19 13:17 UTC

   We're currently investigating an issue affecting users on our Universal 3.5 Pro Realtime model, where new streaming sessions could not be created on our EU endpoint. This occurred from 13:00–13:12 UTC. Affected users are seeing a 3005 close code. Users on the US endpoint are...

2. identified 2026-08-19 13:17 UTC

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

3. monitoring 2026-08-19 13:18 UTC

   A fix has been implemented and our team is monitoring the results. Users can now create new realtime sessions successfully.

4. monitoring 2026-08-19 13:20 UTC

   We are continuing to monitor for any further issues.

5. resolved 2026-08-19 13:24 UTC

   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.

Excerpts are shortened. Read the full incident on AssemblyAI's status page.

Affected: Asynchronous API

Failure mode: Exhausted memory, disk, CPU, queues, connection pools or quotas. Root cause: The vendor does not say why it happened. Tagged by claude-haiku-5-5 with medium confidence (taxonomy v0.2).

1. investigating 2026-08-18 19:34 UTC

   We're currently seeing longer than usual processing times for asynchronous transcription requests using Universal-3 Pro and Universal-3.5 Pro. Requests are being accepted and are completing, but time to completion is elevated while our queues work through a backlog.

2. identified 2026-08-18 19:46 UTC

   We have identified the cause of the elevated processing times affecting pre-recorded transcription requests using Universal-3 Pro and Universal-3.5 Pro. Our engineering team has addressed a capacity constraint and is working to restore full capacity. Processing times will remain...

3. monitoring 2026-08-18 19:55 UTC

   Processing times for pre-recorded transcription requests using Universal-3 Pro and Universal-3.5 Pro are returning to normal ranges and the backlog has largely cleared. We are continuing to monitor to ensure stability.

4. resolved 2026-08-18 20:12 UTC

   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.

Excerpts are shortened. Read the full incident on AssemblyAI's status page.

Affected: Asynchronous API

Failure mode: Data delayed, stale, lost or corrupted, or needing replay after recovery. Root cause: The vendor does not say why it happened. Tagged by claude-haiku-5-5 with medium confidence (taxonomy v0.2).

1. investigating 2026-08-14 14:49 UTC

   We are currently investigating an issue that is affecting webhook delivery on our Async EU Endpoint. This began at 2:30p UTC. Customers are receiving delayed webhook deliveries on the EU endpoint. This does not affect customers using webhooks on our US endpoint.

2. identified 2026-08-14 14:59 UTC

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

3. monitoring 2026-08-14 15:03 UTC

   A fix has been implemented and we are monitoring the results.

4. resolved 2026-08-14 15:09 UTC

   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.

Excerpts are shortened. Read the full incident on AssemblyAI's status page.

Affected: Streaming API

Failure mode: A code release introduced the failure. Root cause: The vendor does not say why it happened. Tagged by claude-haiku-5-5 with low confidence (taxonomy v0.2).

Names an upstream provider: AWS.

1. investigating 2026-08-03 16:08 UTC

   We are currently investigating an issue where users on our us-east-1 endpoint are experiencing 503 errors when using temporary tokens with our Realtime API. This began at 4:49pm UTC.

2. identified 2026-08-03 16:11 UTC

   Our team has identified the issue and a fix is being released.

3. identified 2026-08-03 16:33 UTC

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

4. monitoring 2026-08-03 16:37 UTC

   A fix has been implemented and we are monitoring the results.

5. resolved 2026-08-03 17:56 UTC

   This incident has been resolved.

Excerpts are shortened. Read the full incident on AssemblyAI's status page.

Failure mode: The text does not say enough to tell. Root cause: The vendor does not say why it happened. Tagged by claude-haiku-5-5 with medium confidence (taxonomy v0.2).

1. resolved 2026-07-31 20:00 UTC

   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. Affected sessions connected successfully but did not process incoming audio, so no transcript was returned while the connection remained open....

Excerpts are shortened. Read the full incident on AssemblyAI's status page.

Affected: Asynchronous API

Failure mode: Exhausted memory, disk, CPU, queues, connection pools or quotas. Root cause: The vendor does not say why it happened. Tagged by claude-haiku-5-5 with medium confidence (taxonomy v0.2).

1. investigating 2026-07-09 13:53 UTC

   We are seeing increased processing times for pre-recorded (async) transcriptions on the US endpoint. Webhook deliveries may also be delayed. We are currently investigating.

2. identified 2026-07-09 13:59 UTC

   We have identified the issue causing elevated processing times for async transcriptions on the US endpoint and have addressed the root cause. The system is recovering, but processing times remain elevated while the backlog clears. Webhook deliveries may also continue to be...

3. monitoring 2026-07-09 14:10 UTC

   We have been monitoring the queue drain and transcription pickup delays caused by the backlog. Processing times are returning to normal ranges on the US endpoint and the backlog has cleared. We are continuing to monitor.

4. resolved 2026-07-09 14:12 UTC

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

Excerpts are shortened. Read the full incident on AssemblyAI's status page.

Failure mode: A zone, region or data center became unavailable. Root cause: The vendor does not say why it happened. Tagged by claude-haiku-5-5 with medium confidence (taxonomy v0.2).

1. resolved 2026-07-07 15:00 UTC

   This 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 did not return transcripts. Sessions already in progress,...

Excerpts are shortened. Read the full incident on AssemblyAI's status page.

Affected: Asynchronous API

Failure mode: Exhausted memory, disk, CPU, queues, connection pools or quotas. Root cause: The vendor does not say why it happened. Tagged by claude-haiku-5-5 with medium confidence (taxonomy v0.2).

1. investigating 2026-06-25 15:37 UTC

   We are currently investigating an issue with async transcriptions on the US endpoint that use speaker labels. This is resulting in timeouts for all transcriptions with speaker labels enabled for files under 2 minutes long. This began at 15:00 UTC.

2. identified 2026-06-25 15:38 UTC

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

3. monitoring 2026-06-25 16:00 UTC

   A fix has been implemented and our API is slowly beginning to recover normal processing.

4. monitoring 2026-06-25 16:14 UTC

   The root cause has been addressed and our system is slowly working through the transcript backlog, which is causing slower processing on our US async endpoint.

5. monitoring 2026-06-25 16:27 UTC

   Our API is continuing to recover and incoming transcriptions are returning to normal processing. We are continuing to monitor the situation.

6. resolved 2026-06-25 16:48 UTC

   This incident has been resolved.

7. postmortem 2026-06-25 18:02 UTC

   **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 transcription pipeline, which slowed and timed out...

Excerpts are shortened. Read the full incident on AssemblyAI's status page.

Affected: Asynchronous API

Failure mode: A zone, region or data center became unavailable. Root cause: The vendor does not say why it happened. Tagged by claude-haiku-5-5 with low confidence (taxonomy v0.2).

1. investigating 2026-06-24 09:13 UTC

   We are currently investigating degradations affecting only traffic to the EU versions of Universal-3Pro and Universal-3-5-pro for pre-recorded audio transcription.

2. identified 2026-06-24 09:34 UTC

   Our engineering team has identified the issue and is actively working to implement a fix. We will continue to provide updates as more information becomes available.

3. monitoring 2026-06-24 10:16 UTC

   A fix has been implemented and requests to the EU versions of Universal-3-Pro and Universal-3-5-Pro no longer show degradations. We are continuing to monitor to ensure stability.

4. resolved 2026-06-24 10:40 UTC

   The 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 disruption to your workflows. If you have any questions, please...

Excerpts are shortened. Read the full incident on AssemblyAI's status page.

Affected: Dashboard

Failure mode: A provider or third-party service this vendor depends on failed. Root cause: A failure at a provider or vendor they depend on. Tagged by claude-haiku-5-5 with high confidence (taxonomy v0.2).

1. investigating 2026-05-27 21:00 UTC

   We are currently experiencing degraded performance with new account signups and provisioning due to an upstream issue with our billing provider. Existing accounts and API usage are unaffected. New users may experience errors or delays when creating an account. Our team is...

2. monitoring 2026-05-27 21:16 UTC

   Account signups and upgrades have recovered and we are seeing successful new account creation. Our team is continuing to monitor and clean up a small number of affected accounts. We will provide a final update once fully resolved.

3. resolved 2026-05-27 22:13 UTC

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

Excerpts are shortened. Read the full incident on AssemblyAI's status page.

Affected: Asynchronous API

Failure mode: The text does not say enough to tell. Root cause: The vendor does not say why it happened. Tagged by claude-haiku-5-5 with medium confidence (taxonomy v0.2).

1. monitoring 2026-05-19 11:08 UTC

   A fix has been implemented and the EU endpoint is recovering. Processing times and error rates are stabilizing.

2. resolved 2026-05-19 15:28 UTC

   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.

Excerpts are shortened. Read the full incident on AssemblyAI's status page.

Affected: Billing

Failure mode: Data delayed, stale, lost or corrupted, or needing replay after recovery. Root cause: The vendor does not say why it happened. Tagged by claude-haiku-5-5 with medium confidence (taxonomy v0.2).

1. investigating 2026-05-07 13:56 UTC

   We are currently investigating an issue affecting billing balance updates and notifications. Some customers may notice that their account balance is not reflecting the most up-to-date usage. Additionally, the following notifications may not be delivered as expected: - Low...

2. identified 2026-05-07 14:27 UTC

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

3. monitoring 2026-05-07 16:34 UTC

   A fix has been implemented and we are monitoring the results.

4. resolved 2026-05-07 17:04 UTC

   This incident has been resolved.

Excerpts are shortened. Read the full incident on AssemblyAI's status page.

Affected: Asynchronous API

Failure mode: Exhausted memory, disk, CPU, queues, connection pools or quotas. Root cause: The vendor does not say why it happened. Tagged by claude-haiku-5-5 with low confidence (taxonomy v0.2).

1. identified 2026-04-16 18:37 UTC

   We have identified an issue that is causing elevated processing times for requests that are using Universal-2 for pre-recorded audio. Most requests are still completing successfully, but we are also seeing a small increase in errors as a result of some requests timing out. Our...

2. monitoring 2026-04-16 18:56 UTC

   The root cause of the slowdown has been addressed and turnaround times have once again returned to the normal range. We will continue to monitor traffic going forward to ensure continued good performance.

3. resolved 2026-04-16 19:24 UTC

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

Excerpts are shortened. Read the full incident on AssemblyAI's status page.

Affected: Asynchronous API, Transcription Queue

Failure mode: Exhausted memory, disk, CPU, queues, connection pools or quotas. Root cause: The vendor does not say why it happened. Tagged by claude-haiku-5-5 with medium confidence (taxonomy v0.2).

1. identified 2026-04-09 21:33 UTC

   We are currently experiencing degraded async transcription performance. Some customers may see increased processing times or throttled requests. Our engineering team has identified the issue and is actively working to restore full capacity. We will continue to provide updates as...

2. monitoring 2026-04-09 21:40 UTC

   The capacity constraint has been addressed and the transcription queue is actively clearing. Processing times should return to normal within the next few minutes. We are continuing to monitor to ensure stability.

3. resolved 2026-04-09 21:49 UTC

   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.

Excerpts are shortened. Read the full incident on AssemblyAI's status page.

Failure mode: A configuration change caused the failure. Root cause: A configuration change. Tagged by claude-haiku-5-5 with high confidence (taxonomy v0.2).

1. resolved 2026-04-06 21:51 UTC

   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 errors for their requests. What happened: A...

Excerpts are shortened. Read the full incident on AssemblyAI's status page.

Affected: LLM Gateway

Failure mode: A provider or third-party service this vendor depends on failed. Root cause: A failure at a provider or vendor they depend on. Tagged by claude-haiku-5-5 with high confidence (taxonomy v0.2).

Names an upstream provider: AWS.

1. identified 2026-03-30 18:41 UTC

   AWS Bedrock is currently experiencing issues that are leading to an increase in errors for Claude models. This increase in errors seems to be primarily with Sonnet 4.6, but could also affect other Claude models. We are working with their team to monitor the status of this issue...

2. identified 2026-03-30 21:54 UTC

   The AWS Bedrock issues affecting some Claude models through LLM Gateway, mainly Sonnet 4.6, are still occurring, but the frequency of those errors has gone down. We are continuing to closely monitor the issue for a resolution.

3. resolved 2026-03-30 23:55 UTC

   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.

Excerpts are shortened. Read the full incident on AssemblyAI's status page.

Affected: Asynchronous API

Failure mode: Exhausted memory, disk, CPU, queues, connection pools or quotas. Root cause: The vendor does not say why it happened. Tagged by claude-haiku-5-5 with low confidence (taxonomy v0.2).

1. resolved 2026-03-06 19:04 UTC

   From 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 are back within normal ranges. Our team will continue to...

Excerpts are shortened. Read the full incident on AssemblyAI's status page.

Affected: Billing

Failure mode: Data delayed, stale, lost or corrupted, or needing replay after recovery. Root cause: The vendor does not say why it happened. Tagged by claude-haiku-5-5 with low confidence (taxonomy v0.2).

1. investigating 2026-02-28 19:19 UTC

   We are aware of an issue that caused unexpected multiple auto-refill charges for a subset of customers using Universal-3-Pro today, February 28, 2025. Our team is actively investigating the root cause and working to resolve it as quickly as possible. We apologize for the...

2. resolved 2026-02-28 20:44 UTC

   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.

Excerpts are shortened. Read the full incident on AssemblyAI's status page.

Affected: LLM Gateway

Failure mode: AI model returned degraded, wrong or empty output (not errors or timeouts). Root cause: The vendor does not say why it happened. Tagged by claude-haiku-5-5 with medium confidence (taxonomy v0.2).

1. investigating 2026-02-27 13:29 UTC

   We are currently investigating an issue that is resulting in degraded Speaker Identification and Translation tasks.

2. identified 2026-02-27 13:30 UTC

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

3. monitoring 2026-02-27 14:47 UTC

   A fix has been implemented and we are monitoring the results.

4. resolved 2026-02-27 15:21 UTC

   This incident has been resolved.

Excerpts are shortened. Read the full incident on AssemblyAI's status page.

Affected: Asynchronous API, Streaming API, Playground, Billing, LLM Gateway

Failure mode: A schema or data migration caused the failure. Root cause: A human mistake during operations. Tagged by claude-haiku-5-5 with medium confidence (taxonomy v0.2).

1. investigating 2026-02-25 19:39 UTC

   We are currently investigating a billing issue affecting a small number of customer accounts. Impacted accounts are receiving a negative balance via the API, which is preventing transcription requests from completing and returning errors instead. Our team is actively working to...

2. identified 2026-02-25 20:34 UTC

   Our team has identified the root cause of the negative balance error currently affecting a small number of accounts. A fix is actively being rolled out and we will continue to monitor the situation closely until full resolution is confirmed.

3. resolved 2026-02-25 21:34 UTC

   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. Our team is continuing to monitor the situation to ensure full stability. We apologize for...

Excerpts are shortened. Read the full incident on AssemblyAI's status page.

Affected: LLM Gateway

Failure mode: A provider or third-party service this vendor depends on failed. Root cause: A failure at a provider or vendor they depend on. Tagged by claude-haiku-5-5 with high confidence (taxonomy v0.2).

Names an upstream provider: AWS.

1. identified 2026-02-09 19:53 UTC

   We have identified an issue with the AWS hosting of our Claude Haiku 4.5 model, which is leading to increased 429 errors when using LLM Gateway with the Haiku 4.5 model. This issue is not currently affecting other LLM Gateway models, and retries for requests using Haiku 4.5 are...

2. monitoring 2026-02-09 22:55 UTC

   The increased error rates with Haiku 4.5 that we were seeing earlier have subsided but we are continuing to monitor traffic on our end to ensure continued good performance.

3. resolved 2026-02-10 00:33 UTC

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

Excerpts are shortened. Read the full incident on AssemblyAI's status page.

Affected: Asynchronous API, Website, Streaming API, Playground, Dashboard, LLM Gateway

Failure mode: Exhausted memory, disk, CPU, queues, connection pools or quotas. Root cause: Not enough capacity for the load. Tagged by claude-haiku-5-5 with high confidence (taxonomy v0.2).

Names an upstream provider: AWS.

1. investigating 2026-01-29 17:54 UTC

   We are currently investigating an issue affecting async + LLM gateway services. More updates to come as we learn more.

2. investigating 2026-01-29 18:02 UTC

   We are continuing to investigate this issue.

3. investigating 2026-01-29 18:09 UTC

   We are currently investigating an issue affecting our Async and LLM Gateway services, which are returning 500 errors. Our team is actively working to identify and resolve the problem. We will provide updates as more information becomes available. All streaming API and EU...

4. investigating 2026-01-29 18:29 UTC

   We are seeing requests beginning to successfully complete and have moved to the monitoring phase. Some requests are still returning 500 errors. Our team continues to actively investigate and monitor the situation. We will provide updates as more information becomes available.

5. monitoring 2026-01-29 18:30 UTC

   We are seeing requests beginning to successfully complete and have moved to the monitoring phase. Some requests are still returning 500 errors. Our website is down, and logins may be affected. Our team continues to actively investigate and monitor the situation. We will provide...

6. monitoring 2026-01-29 18:42 UTC

   We are continuing to see requests being completed. We are working through a backlog of requests, resulting in elevated turnaround times while we recover. Our team continues to actively monitor the situation. We will provide updates as more information becomes available.

7. monitoring 2026-01-29 19:18 UTC

   We are continuing to work through the backlog, and turnaround times are improving. Our team continues to actively monitor the situation. We will provide updates as more information becomes available.

8. resolved 2026-01-29 19:32 UTC

   We have cleared the backlog, and turnaround times are back to normal. Our team continues to actively monitor the situation. We will provide a post-mortem when available.

9. postmortem 2026-02-05 18:35 UTC

   **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 increasing and we received an influx of batch transcription jobs...

Excerpts are shortened. Read the full incident on AssemblyAI's status page.

Affected: Asynchronous API

Failure mode: A provider or third-party service this vendor depends on failed. Root cause: A failure at a provider or vendor they depend on. Tagged by claude-haiku-5-5 with high confidence (taxonomy v0.2).

Names an upstream provider: AWS.

1. investigating 2026-01-28 17:50 UTC

   Our team is actively investigating an issue that is causing increased latency for transcriptions using the EU endpoint for pre-recorded transcriptions. Customers may experience transcripts being queued. This is not affecting streaming usage on the EU endpoint.

2. investigating 2026-01-28 18:06 UTC

   This issue is also affecting the EU DELETE endpoint. Some DELETE requests for transcriptions are resulting in an error.

3. identified 2026-01-28 18:39 UTC

   The team has identified the issue and it is caused by an AWS Operational Issue on their Amazon Elastic Compute Cloud (Ireland). Our team is in touch with AWS and monitoring the situation: https://health.aws.amazon.com/health/status

4. monitoring 2026-01-28 19:02 UTC

   We are seeing significant signs of recovery and processing of queued transcripts. Our team will continue to monitor the situation.

5. resolved 2026-01-28 19:58 UTC

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

Excerpts are shortened. Read the full incident on AssemblyAI's status page.

Affected: Streaming API

Failure mode: A configuration change caused the failure. Root cause: A configuration change. Tagged by claude-haiku-5-5 with high confidence (taxonomy v0.2).

1. investigating 2026-01-05 16:45 UTC

   We experienced a spike in connection issues for new streaming sessions between 8:30 and 8:35am PT. These errors affected requests for both NA and EU regions. These connection issues have subsided, but our team is working to ensure continued good performance.

2. resolved 2026-01-05 17:03 UTC

   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. We have continued to see good performance since that rollback and are now marking this issue as resolved.

Excerpts are shortened. Read the full incident on AssemblyAI's status page.

Affected: LLM Gateway

Failure mode: AI model returned degraded, wrong or empty output (not errors or timeouts). Root cause: The vendor does not say why it happened. Tagged by claude-haiku-5-5 with medium confidence (taxonomy v0.2).

1. investigating 2025-11-24 22:39 UTC

   We are currently investigating an issue with LLM Gateway that is causing unexpected responses when using Claude models. This issue is not affecting LLM Gateway requests using other models. We are working to identify and resolve the root cause of these issues.

2. identified 2025-11-25 00:22 UTC

   We have identified the root cause of this issue and are working to release a fix.

3. monitoring 2025-11-25 01:15 UTC

   We have released a fix that has resolved the unexpected responses we were seeing when Claude models were used. Everything is working normally now, but we will continue to monitor traffic to ensure continued good performance.

4. resolved 2025-11-25 01:45 UTC

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

Excerpts are shortened. Read the full incident on AssemblyAI's status page.

Affected: Asynchronous API

Failure mode: A zone, region or data center became unavailable. Root cause: The vendor does not say why it happened. Tagged by claude-haiku-5-5 with medium confidence (taxonomy v0.2).

1. investigating 2025-11-20 08:21 UTC

   We are currently investigating an issue where there has been delayed processing of transcripts on Slam-1, specifically in our us-west-2 region. This began at 5:43 UTC. Customers will experience queueing or erroring of transcripts when using our Slam-1 model. Our Universal model...

2. identified 2025-11-20 08:26 UTC

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

3. monitoring 2025-11-20 08:47 UTC

   A fix has been implemented and our team is monitoring the results. Slam-1 has resumed normal processing.

4. resolved 2025-11-20 09:41 UTC

   This incident has been resolved.

Excerpts are shortened. Read the full incident on AssemblyAI's status page.

Affected: Website, Dashboard

Failure mode: A provider or third-party service this vendor depends on failed. Root cause: A failure at a provider or vendor they depend on. Tagged by claude-haiku-5-5 with high confidence (taxonomy v0.2).

Names an upstream provider: Cloudflare.

1. investigating 2025-11-18 14:15 UTC

   Due to the ongoing incident with Cloudflare, our documentation is unable to be accessed and users cannot use Google Authentication to sign in to their dashboard.

2. identified 2025-11-18 14:23 UTC

   Due to the ongoing incident with Cloudflare, our documentation is unable to be accessed and users cannot use Google Authentication to sign in to their dashboard.

3. monitoring 2025-11-18 15:15 UTC

   Our documentation is now accessible and all users can sign-in to the dashboard using Google Authentication. We will continue to monitor the situation in case anything changes.

4. resolved 2025-11-18 20:58 UTC

   Cloudflare 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.

Excerpts are shortened. Read the full incident on AssemblyAI's status page.

Failure mode: Login, tokens, certificates or credentials failed. Root cause: A configuration change. Tagged by claude-haiku-5-5 with medium confidence (taxonomy v0.2).

1. resolved 2025-11-15 14:30 UTC

   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.com/v3/ws` from Europe, Africa, and eastern Asia were experiencing SSL certificate validation errors. While the underlying...

Excerpts are shortened. Read the full incident on AssemblyAI's status page.

Affected: Asynchronous API

Failure mode: Exhausted memory, disk, CPU, queues, connection pools or quotas. Root cause: The vendor does not say why it happened. Tagged by claude-haiku-5-5 with low confidence (taxonomy v0.2).

1. investigating 2025-10-31 10:38 UTC

   We are currently investigating an issue that is leading to longer-than-usual processing times for pre-recorded audio transcriptions using the Slam-1 model that is resulting in some transcripts being returned with server errors. Requests using the Universal model, which is...

2. investigating 2025-10-31 10:39 UTC

   We are continuing to investigate this issue.

3. identified 2025-10-31 10:42 UTC

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

4. monitoring 2025-10-31 11:49 UTC

   A fix has been implemented and we are monitoring the results.

5. resolved 2025-10-31 13:27 UTC

   This incident has been resolved.

Excerpts are shortened. Read the full incident on AssemblyAI's status page.

Affected: Asynchronous API

Failure mode: AI model returned degraded, wrong or empty output (not errors or timeouts). Root cause: The vendor does not say why it happened. Tagged by claude-haiku-5-5 with medium confidence (taxonomy v0.2).

1. investigating 2025-10-30 19:36 UTC

   We are currently investigating an issue that is leading to longer-than-usual processing times for pre-recorded audio transcriptions using the Slam-1 model. Requests using the Universal model, which is enabled by default, are not affected by this issue.

2. identified 2025-10-30 19:51 UTC

   Our team has identified the issue causing the delay in processing requests using Slam-1 and is actively working to resolve the issue.

3. identified 2025-10-30 20:06 UTC

   We are currently seeing some Slam-1 requests fail with a server error as we are restarting services while working to address this issue. We suggest holding off on retries for the time being or retrying those requests using Universal until normal processing has been restored. We...

4. identified 2025-10-30 21:21 UTC

   We are starting to see success rates return to the normal range, but we are still working to ensure that the issue has been fully resolved.

5. monitoring 2025-10-30 21:42 UTC

   We are continuing to see success rates in the normal range and no longer than usual processing times but we will continue to monitor traffic to ensure continued good performance.

6. identified 2025-10-30 23:47 UTC

   We are once again seeing occasional issues where some requests using the Slam-1 model are taking longer than normal to process or failing with a server error. Retries are typically successful and requests using the Universal model are unaffected.

7. monitoring 2025-10-31 01:26 UTC

   Success rates and processing times have returned to the normal range, but we are monitoring traffic to ensure continued good performance.

8. resolved 2025-10-31 02:21 UTC

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

Excerpts are shortened. Read the full incident on AssemblyAI's status page.

Affected: Asynchronous API

Failure mode: The text does not say enough to tell. Root cause: The vendor does not say why it happened. Tagged by claude-haiku-5-5 with medium confidence (taxonomy v0.2).

1. identified 2025-10-22 17:56 UTC

   We are currently seeing longer-than-usual turnaround times for pre-recorded audio transcriptions that are using our Slam-1 model. Requests using the Universal model are unaffected. We are working to address this issue and will provide an update here as soon as possible.

2. identified 2025-10-22 18:01 UTC

   We are now seeing increased error rates and failures for requests using the Slam-1 model so we are elevating this issue to a partial outage. Requests using Universal are working normally, so consider using that model as a short-term workaround if needed. Our team is working to...

3. identified 2025-10-22 19:03 UTC

   We are once again starting to see requests using Slam-1 succeed, but we are still working to fully resolve the issue. We will follow up with another update once the issue has been fully mitigated.

4. identified 2025-10-22 19:20 UTC

   We are still seeing good success rates for requests using the Slam-1 model, but we are still seeing occasional slower-than-usual processing times, which we are working to address.

5. monitoring 2025-10-22 19:37 UTC

   Success rates and turnaround times for requests using Slam-1 have returned to normal ranges, but we are continuing to monitor traffic to ensure continued good performance.

6. resolved 2025-10-22 23:58 UTC

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

Excerpts are shortened. Read the full incident on AssemblyAI's status page.

Affected: Billing

Failure mode: A provider or third-party service this vendor depends on failed. Root cause: A failure at a provider or vendor they depend on. Tagged by claude-haiku-5-5 with high confidence (taxonomy v0.2).

Names an upstream provider: AWS.

1. identified 2025-10-20 23:00 UTC

   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.

2. monitoring 2025-10-20 23:39 UTC

   Account creation and updates are once again working normally, but we are continuing to monitor the situation to ensure continued good performance.

3. resolved 2025-10-21 00:29 UTC

   This incident has been resolved.

Excerpts are shortened. Read the full incident on AssemblyAI's status page.

Affected: Asynchronous API

Failure mode: The text does not say enough to tell. Root cause: The vendor does not say why it happened. Tagged by claude-haiku-5-5 with medium confidence (taxonomy v0.2).

1. investigating 2025-09-30 17:33 UTC

   Our team is currently investigating an issue that is causing an increase in server errors for our pre-recorded audio speech-to-text feature. This issue is only affecting a small number of requests, but it is affecting requests to both Universal and Slam-1 models. If you...

2. identified 2025-09-30 18:25 UTC

   Our team has identified where the errors are occurring in our pipeline and is currently working to identify and resolve the root cause. This issue is currently only affecting an extremely small percentage of total pre-recorded audio traffic. 99%+ of requests are still completing...

3. monitoring 2025-09-30 19:28 UTC

   We have released a fix to address the small increase in errors we were seeing and are monitoring to ensure continued good performance.

4. resolved 2025-09-30 20:28 UTC

   We have continued to see good performance for pre-recorded audio so we are now marking this issue as resolved.

Excerpts are shortened. Read the full incident on AssemblyAI's status page.

Affected: Streaming API

Failure mode: A code release introduced the failure. Root cause: A bug in the vendor's own code. Tagged by claude-haiku-5-5 with medium confidence (taxonomy v0.2).

1. investigating 2025-09-29 13:49 UTC

   Between 1:30p and 1:40p GMT there were an increased number of new streaming sessions that were failing to be established. Customers would have received the error message "received 3005 (registered) Session Cancelled: An error occurred; ".

2. investigating 2025-09-29 13:50 UTC

   The Streaming API has now returned to full functionality. Our team is still investigating the root cause of this issue.

3. investigating 2025-09-29 15:41 UTC

   Our team is still investigating the cause of the elevated errors, but the Streaming API is still continuing to function normally.

4. monitoring 2025-09-29 19:32 UTC

   We have continued to see stable performance throughout the day. The Streaming API is operating normally and we are monitoring the effects of recent changes to ensure continued service stability. Our team continues working to determine the root cause of the earlier connection...

5. resolved 2025-09-30 01:31 UTC

   We 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.

Excerpts are shortened. Read the full incident on AssemblyAI's status page.

Failure mode: Data delayed, stale, lost or corrupted, or needing replay after recovery. Root cause: The vendor does not say why it happened. Tagged by claude-haiku-5-5 with low confidence (taxonomy v0.2).

1. resolved 2025-09-23 10:00 UTC

   From 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 and all transcriptions should now be processing normally.

Excerpts are shortened. Read the full incident on AssemblyAI's status page.

Affected: Asynchronous API

Failure mode: Exhausted memory, disk, CPU, queues, connection pools or quotas. Root cause: The vendor does not say why it happened. Tagged by claude-haiku-5-5 with low confidence (taxonomy v0.2).

1. investigating 2025-09-22 19:34 UTC

   We are currently investigating an issue that is causing a small increase in turnaround times for STT services for pre-recorded audio for some requests. Traffic as a whole is still completing within the range of normal turnaround times. We will provide additional updates as we...

2. resolved 2025-09-22 19:49 UTC

   Aside 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 issue.

Excerpts are shortened. Read the full incident on AssemblyAI's status page.

Failure mode: The text does not say enough to tell. Root cause: The vendor does not say why it happened. Tagged by claude-haiku-5-5 with medium confidence (taxonomy v0.2).

1. resolved 2025-09-16 09:00 UTC

   We 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 our Streaming API is now functioning normally.

Excerpts are shortened. Read the full incident on AssemblyAI's status page.

Affected: Asynchronous API

Failure mode: Exhausted memory, disk, CPU, queues, connection pools or quotas. Root cause: Not enough capacity for the load. Tagged by claude-haiku-5-5 with low confidence (taxonomy v0.2).

1. investigating 2025-08-05 16:05 UTC

   We are currently investigating an issue with Slam-1 that is preventing the successful completion of transcription requests using the model. We will share additional information as it becomes available. Please note this issue is only affecting requests using Slam-1 as the...

2. investigating 2025-08-05 16:14 UTC

   We are continuing to investigate the issues affecting Slam-1. Currently, all requests using Slam-1 as the `speech_model` are failing with a "Server error, developers have been alerted" error. Our team is working to resolve this issue as quickly as possible. Note: This issue is...

3. monitoring 2025-08-05 16:23 UTC

   We have resolved the issue that was affecting Slam-1 and are now seeing requests being processed successfully. We will continue to monitor traffic to ensure good performance, but everything is working as expected at the moment.

4. identified 2025-08-05 16:42 UTC

   We are once again experiencing issues with Slam-1 where requests are failing with a "Server error, developers have been alerted" error. Note: This issue is only affecting requests using Slam-1 as the `speech_model`. Changing the `speech_model` to Universal will allow requests to...

5. identified 2025-08-05 16:53 UTC

   We are seeing Slam-1 requests complete successfully once again, but we are still working to fully resolve the root cause of this issue.

6. identified 2025-08-05 17:16 UTC

   We are still seeing good performance with the Slam model and requests completing as expected, but we are still working to fully resolve the root cause to prevent issues in the future.

7. monitoring 2025-08-05 19:38 UTC

   We have continued to see good performance with no instances of increased errors over the last couple of hours ,but are continuing to monitor to ensure there are no further issues.

8. resolved 2025-08-05 23:15 UTC

   We have continued to see good performance for the last ~6 hours so we are marking this issue as resolved. To prevent future issues, we have made some improvements to allow Slam-1 to scale more effectively.

Excerpts are shortened. Read the full incident on AssemblyAI's status page.

Affected: Dashboard

Failure mode: Data delayed, stale, lost or corrupted, or needing replay after recovery. Root cause: The vendor does not say why it happened. Tagged by claude-haiku-5-5 with medium confidence (taxonomy v0.2).

1. investigating 2025-07-30 09:05 UTC

   We are currently investigating an issue where there is a delay in new transcriptions showing up under the Transcription History tab of the dashboard.

2. investigating 2025-07-30 10:02 UTC

   Our team is still currently investigating the root cause of this delay.

3. identified 2025-07-30 11:48 UTC

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

4. monitoring 2025-07-30 12:57 UTC

   A fix has been implemented and all customer dashboards should now be up to date. We are continuing to monitor the situation.

5. resolved 2025-07-30 13:52 UTC

   This incident has been resolved.

Excerpts are shortened. Read the full incident on AssemblyAI's status page.

Affected: Asynchronous API

Failure mode: Exhausted memory, disk, CPU, queues, connection pools or quotas. Root cause: The vendor does not say why it happened. Tagged by claude-haiku-5-5 with low confidence (taxonomy v0.2).

1. resolved 2025-07-28 15:33 UTC

   We had a brief period earlier where processing times for requests using the Slam-1 beta model took longer than expected. This slowdown occurred from approximately 7:37am PT to 7:57am PT and has now been resolved. Our team is continuing to monitor traffic to ensure continued good...

Excerpts are shortened. Read the full incident on AssemblyAI's status page.

Affected: Asynchronous API

Failure mode: AI model returned degraded, wrong or empty output (not errors or timeouts). Root cause: The vendor does not say why it happened. Tagged by claude-haiku-5-5 with medium confidence (taxonomy v0.2).

1. investigating 2025-07-14 15:38 UTC

   We are experiencing a formatting issue affecting English transcripts. Transcripts will continue to process successfully, but formatting may appear incorrect or incomplete. We're actively investigating this issue.

2. monitoring 2025-07-14 15:59 UTC

   The English transcript formatting issue is now considered resolved. We are monitoring to ensure continued stability. Please re-run any affected transcripts to ensure correct formatting.

3. resolved 2025-07-14 16:47 UTC

   This incident has been resolved.

Excerpts are shortened. Read the full incident on AssemblyAI's status page.