Gladia

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 medium confidence (taxonomy v0.2).

1. investigating 2026-10-07 13:00 UTC

   Service is unhealthy

2. investigating 2026-10-07 13:16 UTC

3. investigating 2026-10-07 13:25 UTC

   Service is coming back online, expect some latency while we process accumulated requests

4. monitoring 2026-10-07 14:04 UTC

   Most of the backlog is cleared. We’re temporarily raising the rate limit to drain the rest as fast as possible. Expect normal operation again in a few minutes.

5. resolved 2026-10-07 14:17 UTC

   Fully recovered. Back to normal operation.

Excerpts are shortened. Read the full incident on Gladia'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 low confidence (taxonomy v0.2).

1. investigating 2026-10-04 11:00 UTC

   Service is unhealthy

2. resolved 2026-10-04 11:26 UTC

   This incident has been resolved.

Excerpts are shortened. Read the full incident on Gladia'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 medium confidence (taxonomy v0.2).

1. identified 2026-10-03 09:26 UTC

   Pre-recorded jobs may be delayed

2. monitoring 2026-10-03 09:37 UTC

   Pre-recorded is recovering.

3. resolved 2026-10-03 09:45 UTC

   Operations are back to normal

Excerpts are shortened. Read the full incident on Gladia'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 low confidence (taxonomy v0.2).

1. investigating 2026-09-28 13:42 UTC

   Service is unhealthy

2. resolved 2026-09-28 13:45 UTC

   This incident has been resolved.

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

Failure mode: Network, DNS, routing or connectivity failure. 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 2026-09-23 14:14 UTC

   Another network incident is affecting our production

2. investigating 2026-09-23 14:24 UTC

   Investigating source of the issue

3. identified 2026-09-23 14:35 UTC

   Network issue affecting Pre-recorded and Real Time. Transcription processing is slower than usual, and file uploads may also be affected. Our team is actively working on a resolution. We will share another update as soon as more information is available.

4. identified 2026-09-23 14:36 UTC

   Network issue affecting Pre-recorded and Real Time. Transcription processing is slower than usual, and file uploads may also be affected. Our team is actively working on a resolution. We will share another update as soon as more information is available.

5. monitoring 2026-09-23 14:53 UTC

   The underlying issue has been mitigated and the platform is stable again. Pre-recorded transcriptions are still taking around 6 minutes on average as we work through the backlog accumulated during the incident. We are monitoring closely and will share another update once...

6. resolved 2026-09-23 15:47 UTC

   The network issue reported by our provider has been resolved, and the platform is stable again. We scaled processing capacity to clear the backlog accumulated during the incident, and the queue is now fully drained. Pre-recorded processing times have returned to an average of...

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

Failure mode: Network, DNS, routing or connectivity failure. Root cause: A failure at a provider or vendor they depend on. Tagged by claude-haiku-5-5 with medium confidence (taxonomy v0.2).

1. investigating 2026-09-23 07:05 UTC

   Investigating source of the issue

2. investigating 2026-09-23 07:14 UTC

   Still Investigating source of the issue.

3. monitoring 2026-09-23 07:33 UTC

   Update : service recovering Situation returning to normal. New Pre-Recorded jobs process normally. Jobs from 08:55–09:34 UTC+2 are processed with delay.

4. resolved 2026-09-23 08:10 UTC

   All services have returned to normal operation. The provider-side network issue is resolved. New jobs are processing normally, and the remaining Pre-Recorded backlog from this morning has been cleared. We consider this incident resolved. Thank you for your patience.

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

Failure mode: Network, DNS, routing or connectivity failure. Root cause: The vendor does not say why it happened. Tagged by claude-haiku-5-5 with medium confidence (taxonomy v0.2).

1. investigating 2026-09-22 17:56 UTC

   We experienced networking issues affecting Pre-recorded and Real time APIs.

2. resolved 2026-09-22 17:58 UTC

   Incident is resolved

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

Failure mode: Network, DNS, routing or connectivity failure. Root cause: Network or DNS. Tagged by claude-haiku-5-5 with medium confidence (taxonomy v0.2).

1. investigating 2026-09-22 17:34 UTC

   We are experiencing timeouts

2. monitoring 2026-09-22 17:53 UTC

   Incident is resolved. We experienced some network issues affecting Real Time.

3. resolved 2026-09-22 17:54 UTC

   Incident is resolved

Excerpts are shortened. Read the full incident on Gladia'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 low confidence (taxonomy v0.2).

1. investigating 2026-09-22 10:22 UTC

   Service is unhealthy

2. resolved 2026-09-22 10:26 UTC

   This incident has been resolved.

Excerpts are shortened. Read the full incident on Gladia'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 low confidence (taxonomy v0.2).

1. investigating 2026-09-21 10:01 UTC

   Service is unhealthy

2. monitoring 2026-09-21 10:37 UTC

   Service is back to normal, monitoring

3. resolved 2026-09-21 12:08 UTC

   This incident has been resolved.

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

Failure mode: Traffic surge or denial-of-service attack. Root cause: Not enough capacity for the load. Tagged by claude-haiku-5-5 with medium confidence (taxonomy v0.2).

1. investigating 2026-09-14 09:07 UTC

   We are currently experiencing degraded performance on our Europe API. Transcription processing is slower than usual, and file uploads may also be affected. Our team is actively working on a resolution. We will share another update as soon as more information is available.

2. monitoring 2026-09-14 10:18 UTC

   We are currently experiencing degraded performance on our Europe API. Transcription processing is slower than usual, and file uploads may also be affected. Our team is actively working on a resolution. We will share another update as soon as more information is available.

3. monitoring 2026-09-14 10:36 UTC

   We have identified the root cause: an external tool generated a traffic spike and a network incident. This delayed transcription processing and impacted our network, which also explains the upload latency. Service is progressively returning to normal. We continue to monitor and...

4. monitoring 2026-09-14 13:02 UTC

   The network issue is now fully resolved. Uploads and API submissions should work normally again. We are still clearing the backlog that built up during the disruption, and we are working to catch up. New jobs are typically completing in around **5 minutes**. Jobs that were...

5. monitoring 2026-09-14 15:01 UTC

   Uploads are working normally again. Processing capacity is still reduced while we clear the backlog from earlier today. Expect around **3 minutes** for new jobs during peak periods, and longer (up to about **20 minutes**) if you have a high volume waiting in the queue. We are...

6. resolved 2026-09-14 16:38 UTC

   Incident is now resolved. The average transcription time is less than 1 minute

7. monitoring 2026-09-15 10:09 UTC

   We are still facing performance issues, requests might take a few minutes to be processed.

8. monitoring 2026-09-15 11:51 UTC

   We are still facing performance issues due to reduced infrastructure capacity. Processing times vary by account: they depend on your current transcription queue and your concurrent processing limit. Across all accounts, average turnaround is currently around 22 minutes. All...

9. monitoring 2026-09-15 13:13 UTC

   We are still facing performance issues due to reduced infrastructure capacity, but average processing times have improved. Across all accounts, average turnaround is currently around 12 minutes. Actual times still vary by account depending on your current transcription queue and...

10. monitoring 2026-09-15 13:58 UTC

    We are still facing performance issues due to reduced infrastructure capacity, average processing times have degraded. Across all accounts, average turnaround is currently around 28 minutes. Actual times still vary by account depending on your current transcription queue and...

11. resolved 2026-09-15 22:38 UTC

    Processing queues are empty and pre-recorded transcription processing times are back to normal. Real-time and live streaming sessions are operating normally. During this incident, some customers experienced elevated error rates, timeouts, and degraded processing times on...

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

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 2026-09-10 09:21 UTC

   Service is unhealthy

2. investigating 2026-09-10 10:18 UTC

   Pre-recorded transcription is taking longer than usual. Average processing time is currently around 6 minutes. Investigation ongoing.

3. monitoring 2026-09-10 10:56 UTC

   Pre-recorded transcription processing times have come down to around 5 minutes on average and are returning to normal. We are monitoring the situation.

4. monitoring 2026-09-10 12:25 UTC

   We have restored our GPU capacity. Due to the earlier incident and ongoing high traffic, pre-recorded transcription processing times remain longer than usual. We continue to monitor the situation closely.

5. resolved 2026-09-10 16:06 UTC

   This issue has been resolved. Pre-recorded transcription processing times have improved further and are now averaging below 4 minutes and are back to normal.

Excerpts are shortened. Read the full incident on Gladia'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 low confidence (taxonomy v0.2).

1. identified 2026-09-02 06:30 UTC

   Real-time API v2 is experiencing intermittent availability and connection failures.

2. resolved 2026-09-02 06:55 UTC

   Service has been restored. Pre-recorded transcription was largely unaffected.

Excerpts are shortened. Read the full incident on Gladia'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 low confidence (taxonomy v0.2).

1. investigating 2026-07-30 14:29 UTC

   Service is unhealthy

2. resolved 2026-07-30 15:10 UTC

   This incident has been resolved.

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

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).

1. investigating 2026-07-26 17:37 UTC

   Service is unhealthy

2. monitoring 2026-07-26 17:51 UTC

   Translation service was overloaded.

3. resolved 2026-07-26 17:52 UTC

   Translation service was scaled to accommodate heavy load.

Excerpts are shortened. Read the full incident on Gladia'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 low confidence (taxonomy v0.2).

1. investigating 2026-07-24 03:49 UTC

   Service is unhealthy

2. resolved 2026-07-24 04:19 UTC

   This incident has been resolved.

Excerpts are shortened. Read the full incident on Gladia'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 low confidence (taxonomy v0.2).

1. investigating 2026-07-19 19:31 UTC

   Service is unhealthy

2. resolved 2026-07-19 20:25 UTC

   This incident has been resolved.

Excerpts are shortened. Read the full incident on Gladia'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 low confidence (taxonomy v0.2).

1. investigating 2026-07-18 17:44 UTC

   Service is unhealthy

2. resolved 2026-07-18 17:50 UTC

   This incident has been resolved.

Excerpts are shortened. Read the full incident on Gladia'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 low confidence (taxonomy v0.2).

1. investigating 2026-07-18 04:55 UTC

   Service is unhealthy

2. resolved 2026-07-18 05:04 UTC

   This incident has been resolved.

Excerpts are shortened. Read the full incident on Gladia'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 low confidence (taxonomy v0.2).

1. investigating 2026-07-15 23:16 UTC

   Service is unhealthy

2. resolved 2026-07-15 23:31 UTC

   This incident has been resolved.

Excerpts are shortened. Read the full incident on Gladia'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 low confidence (taxonomy v0.2).

1. investigating 2026-07-09 19:24 UTC

   Service is unhealthy

2. resolved 2026-07-10 07:16 UTC

   This incident has been resolved.

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

Failure mode: Network, DNS, routing or connectivity failure. Root cause: The vendor does not say why it happened. Tagged by claude-haiku-5-5 with medium confidence (taxonomy v0.2).

1. investigating 2026-07-07 20:50 UTC

   There is a connectivity issue causing huge slow downs in transcriptions. We are working on identifying the root cause.

2. monitoring 2026-07-07 21:37 UTC

   We've identified to the root cause. We are in recovery and monitoring the situation.

3. resolved 2026-07-07 22:24 UTC

   The incident has been resolved. All pending jobs have been processed successfully.

Excerpts are shortened. Read the full incident on Gladia'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 low confidence (taxonomy v0.2).

1. investigating 2026-07-06 20:25 UTC

   Service is unhealthy

2. resolved 2026-07-06 20:28 UTC

   This incident has been resolved.

Excerpts are shortened. Read the full incident on Gladia'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 2026-07-03 15:02 UTC

   Timeframe: 5:02 PM – 5:08 PM Paris Time (CET/CEST) Update: We experienced a brief period of elevated latency and intermittent timeouts affecting the Gladia API. Our engineering team monitored the situation, and performance has since fully stabilized. All systems are now...

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

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 2026-06-18 09:05 UTC

   Service is unhealthy

2. investigating 2026-06-18 10:31 UTC

   We are still investigating degraded performance on pre-recorded transcription in Europe. On our side, current average end-to-end latency for jobs in the EU pipeline is about **15 minutes**. Most of that time is spent waiting in the processing queue (~10 minutes), with the actual...

3. monitoring 2026-06-18 11:29 UTC

   We have applied mitigations and pre-recorded transcription performance in Europe is now back to normal levels for new jobs. Average end-to-end latency for new transcriptions in the EU pipeline is approximately **3 minutes**, in line with our usual operating range. Queue wait is...

4. resolved 2026-06-18 12:13 UTC

   This incident is now resolved. Pre-recorded transcription in Europe is operating normally. Average end-to-end latency for new jobs in the EU pipeline is approximately **25 seconds**, with queue wait under **10 seconds** and transcription completing in about **20 seconds** on...

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