Gladia Outage History
Gladia is up right nowPingoru has recorded 52 incidents for Gladia: 52 in the last 12 months and 13 in the last 90 days.
Show as a table
| Month | Incidents | Hours with an open incident |
|---|---|---|
| April 2026 | 9 | 11 of 720 (2%) |
| May 2026 | 3 | 7 of 744 (1%) |
| June 2026 | 2 | 11 of 720 (1%) |
| July 2026 | 12 | 16 of 744 (2%) |
| August 2026 | 0 | 0 of 744 (0%) |
| September 2026 | 10 | 48 of 720 (7%) |
| October 2026 | 3 | 2 of 744 (0%) |
| November 2026 | 0 | 0 of 140 (0%) |
Incidents, newest first
Critical October 7, 2026 [Europe] Pre-Recorded is in a degraded state 1h 16m Pre-Recorded (Pre-Recorded v2)
Started Oct 07, 2026, 01:00 PM UTC· resolved Oct 07, 2026, 02:17 PM UTC
- investigating Oct 07, 2026, 01:00 PM UTC
Service is unhealthy
- investigating Oct 07, 2026, 01:16 PM UTC
https://public-cloud.status-ovhcloud.com/incidents/kdqq2smzfd4t
- investigating Oct 07, 2026, 01:25 PM UTC
Service is coming back online, expect some latency while we process accumulated requests
- monitoring Oct 07, 2026, 02:04 PM 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.
- resolved Oct 07, 2026, 02:17 PM UTC
Fully recovered. Back to normal operation.
Minor October 4, 2026 [Europe] Pre-Recorded is in a degraded state 26m Application (Add-ons)
Started Oct 04, 2026, 11:00 AM UTC· resolved Oct 04, 2026, 11:26 AM UTC
- investigating Oct 04, 2026, 11:00 AM UTC
Service is unhealthy
- resolved Oct 04, 2026, 11:26 AM UTC
This incident has been resolved.
Minor October 3, 2026 [Europe] Pre-Recorded is in degraded state 11m Pre-Recorded (Pre-Recorded v2)
Started Oct 03, 2026, 09:26 AM UTC· resolved Oct 03, 2026, 09:37 AM UTC
- identified Oct 03, 2026, 09:26 AM UTC
Pre-recorded jobs may be delayed
- monitoring Oct 03, 2026, 09:37 AM UTC
Pre-recorded is recovering.
- resolved Oct 03, 2026, 09:45 AM UTC
Operations are back to normal
Minor September 28, 2026 [Europe] Add-ons is in a degraded state 2m Application (Add-ons)
Started Sep 28, 2026, 01:42 PM UTC· resolved Sep 28, 2026, 01:45 PM UTC
- investigating Sep 28, 2026, 01:42 PM UTC
Service is unhealthy
- resolved Sep 28, 2026, 01:45 PM UTC
This incident has been resolved.
Critical September 23, 2026 Real-time and Pre-recorded is having issue 1h 12m Application (Website), Application (Add-ons), Application (Playground), Real-Time (Real-Time v2) and 3 more
Started Sep 23, 2026, 02:35 PM UTC· resolved Sep 23, 2026, 03:47 PM UTC
- investigating Sep 23, 2026, 02:14 PM UTC
Another network incident is affecting our production
- investigating Sep 23, 2026, 02:24 PM UTC
Investigating source of the issue
- identified Sep 23, 2026, 02:35 PM 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.
- identified Sep 23, 2026, 02:36 PM 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.
- monitoring Sep 23, 2026, 02:53 PM 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 processing times return to normal.
- resolved Sep 23, 2026, 03:47 PM 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 around 15 seconds. Real-Time is stable.
Critical September 23, 2026 Global Incident - Pre-Recorded / Real-Time 38m Application (Website), Application (Add-ons), Application (Playground), Real-Time (Real-Time v2) and 3 more
Started Sep 23, 2026, 06:55 AM UTC· resolved Sep 23, 2026, 07:33 AM UTC
- investigating Sep 23, 2026, 07:05 AM UTC
Investigating source of the issue
- investigating Sep 23, 2026, 07:14 AM UTC
Still Investigating source of the issue.
- monitoring Sep 23, 2026, 07:33 AM 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.
- resolved Sep 23, 2026, 08:10 AM 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.
Minor September 22, 2026 Timeouts 20m
Started Sep 22, 2026, 05:34 PM UTC· resolved Sep 22, 2026, 05:54 PM UTC
- investigating Sep 22, 2026, 05:34 PM UTC
We are experiencing timeouts
- monitoring Sep 22, 2026, 05:53 PM UTC
Incident is resolved. We experienced some network issues affecting Real Time.
- resolved Sep 22, 2026, 05:54 PM UTC
Incident is resolved
Critical September 22, 2026 Real Time outage 18m Real-Time (Real-Time v2), Pre-Recorded (Pre-Recorded v2), Real-Time (Real-Time v1)
Started Sep 22, 2026, 05:20 PM UTC· resolved Sep 22, 2026, 05:38 PM UTC
- investigating Sep 22, 2026, 05:56 PM UTC
We experienced networking issues affecting Pre-recorded and Real time APIs.
- resolved Sep 22, 2026, 05:58 PM UTC
Incident is resolved
Minor September 22, 2026 [Europe] Add-ons is in a degraded state 4m Application (Add-ons)
Started Sep 22, 2026, 10:22 AM UTC· resolved Sep 22, 2026, 10:26 AM UTC
- investigating Sep 22, 2026, 10:22 AM UTC
Service is unhealthy
- resolved Sep 22, 2026, 10:26 AM UTC
This incident has been resolved.
Minor September 21, 2026 [Europe] API is in a degraded state 36m Application (API)
Started Sep 21, 2026, 10:01 AM UTC· resolved Sep 21, 2026, 10:37 AM UTC
- investigating Sep 21, 2026, 10:01 AM UTC
Service is unhealthy
- monitoring Sep 21, 2026, 10:37 AM UTC
Service is back to normal, monitoring
- resolved Sep 21, 2026, 12:08 PM UTC
This incident has been resolved.
Minor September 14, 2026 [Europe] API is in a degraded state 1d 13h Application (Add-ons), Pre-Recorded (Pre-Recorded v2)
Started Sep 14, 2026, 09:07 AM UTC· resolved Sep 15, 2026, 10:38 PM UTC
- investigating Sep 14, 2026, 09:07 AM 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.
- monitoring Sep 14, 2026, 10:18 AM 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.
- monitoring Sep 14, 2026, 10:36 AM 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 will share a final update once everything is confirmed stable.
- monitoring Sep 14, 2026, 01:02 PM 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 already waiting, or accounts with a large queue, can still see longer processing times until that backlog drains. We will keep monitoring and share another update as processing returns to normal.
- monitoring Sep 14, 2026, 03:01 PM 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 continuing to improve capacity and will update again as times return to normal.
- resolved Sep 14, 2026, 04:38 PM UTC
Incident is now resolved. The average transcription time is less than 1 minute
- monitoring Sep 15, 2026, 10:09 AM UTC
We are still facing performance issues, requests might take a few minutes to be processed.
- monitoring Sep 15, 2026, 11:51 AM 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 transcriptions are still being processed and are not lost. Some may simply complete more slowly than usual. Our teams continue to work on restoring full capacity.
- monitoring Sep 15, 2026, 01:13 PM 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 your concurrent processing limit. All transcriptions are still being processed. Some may simply complete more slowly than usual. Our teams continue to work on restoring full capacity.
- monitoring Sep 15, 2026, 01:58 PM 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 your concurrent processing limit. All transcriptions are still being processed. Some may simply complete more slowly than usual. Our teams continue to work on restoring full capacity.
- resolved Sep 15, 2026, 10:38 PM 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 pre-recorded, real-time, and live streaming endpoints. A detailed post-mortem will be shared in the coming days. We sincerely apologize for the disruption and thank you for your patience.
Minor September 10, 2026 [Europe] Pre-Recorded is in a degraded state 6h 44m Pre-Recorded (Pre-Recorded v2)
Started Sep 10, 2026, 09:21 AM UTC· resolved Sep 10, 2026, 04:06 PM UTC
- investigating Sep 10, 2026, 09:21 AM UTC
Service is unhealthy
- investigating Sep 10, 2026, 10:18 AM UTC
Pre-recorded transcription is taking longer than usual. Average processing time is currently around 6 minutes. Investigation ongoing.
- monitoring Sep 10, 2026, 10:56 AM 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.
- monitoring Sep 10, 2026, 12:25 PM 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.
- resolved Sep 10, 2026, 04:06 PM 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.
Minor September 2, 2026 [Europe] Real Time V2 degraded state 25m Real-Time (Real-Time v2)
Started Sep 02, 2026, 06:30 AM UTC· resolved Sep 02, 2026, 06:55 AM UTC
- identified Sep 02, 2026, 06:30 AM UTC
Real-time API v2 is experiencing intermittent availability and connection failures.
- resolved Sep 02, 2026, 06:55 AM UTC
Service has been restored. Pre-recorded transcription was largely unaffected.
Minor July 30, 2026 Pyannote Modal diarization failing (DNS) — empty speakers –
Started Jul 30, 2026, 04:07 PM UTC· resolved Jul 30, 2026, 04:07 PM UTC
- investigating Jul 30, 2026, 04:06 PM UTC
Service is unhealthy
- resolved Jul 30, 2026, 04:07 PM UTC
This incident has been resolved.
Minor July 30, 2026 [Europe] Pre-Recorded is in a degraded state 40m Pre-Recorded (Pre-Recorded v2)
Started Jul 30, 2026, 02:29 PM UTC· resolved Jul 30, 2026, 03:10 PM UTC
- investigating Jul 30, 2026, 02:29 PM UTC
Service is unhealthy
- resolved Jul 30, 2026, 03:10 PM UTC
This incident has been resolved.
Minor July 26, 2026 [Europe] Translations are in a degraded state 14m Application (Add-ons)
Started Jul 26, 2026, 05:37 PM UTC· resolved Jul 26, 2026, 05:52 PM UTC
- investigating Jul 26, 2026, 05:37 PM UTC
Service is unhealthy
- monitoring Jul 26, 2026, 05:51 PM UTC
Translation service was overloaded.
- resolved Jul 26, 2026, 05:52 PM UTC
Translation service was scaled to accommodate heavy load.
Minor July 24, 2026 [Europe] Add-ons is in a degraded state 30m Application (Add-ons)
Started Jul 24, 2026, 03:49 AM UTC· resolved Jul 24, 2026, 04:19 AM UTC
- investigating Jul 24, 2026, 03:49 AM UTC
Service is unhealthy
- resolved Jul 24, 2026, 04:19 AM UTC
This incident has been resolved.
Minor July 19, 2026 [Europe] API is in a degraded state 53m Application (API)
Started Jul 19, 2026, 07:31 PM UTC· resolved Jul 19, 2026, 08:25 PM UTC
- investigating Jul 19, 2026, 07:31 PM UTC
Service is unhealthy
- resolved Jul 19, 2026, 08:25 PM UTC
This incident has been resolved.
Minor July 18, 2026 [Europe] Real-Time v2 is in a degraded state 6m Application (Add-ons)
Started Jul 18, 2026, 05:44 PM UTC· resolved Jul 18, 2026, 05:50 PM UTC
- investigating Jul 18, 2026, 05:44 PM UTC
Service is unhealthy
- resolved Jul 18, 2026, 05:50 PM UTC
This incident has been resolved.
Minor July 18, 2026 [Europe] API is in a degraded state 9m
Started Jul 18, 2026, 04:55 AM UTC· resolved Jul 18, 2026, 05:04 AM UTC
- investigating Jul 18, 2026, 04:55 AM UTC
Service is unhealthy
- resolved Jul 18, 2026, 05:04 AM UTC
This incident has been resolved.
Minor July 15, 2026 [Europe] Pre-Recorded is in a degraded state 15m Application (Add-ons)
Started Jul 15, 2026, 11:16 PM UTC· resolved Jul 15, 2026, 11:31 PM UTC
- investigating Jul 15, 2026, 11:16 PM UTC
Service is unhealthy
- resolved Jul 15, 2026, 11:31 PM UTC
This incident has been resolved.
Minor July 9, 2026 [Europe] Add-ons Sentiment Analysis Failures 11h 51m Application (Add-ons)
Started Jul 09, 2026, 07:24 PM UTC· resolved Jul 10, 2026, 07:16 AM UTC
- investigating Jul 09, 2026, 07:24 PM UTC
Service is unhealthy
- resolved Jul 10, 2026, 07:16 AM UTC
This incident has been resolved.
Major July 7, 2026 Slow transcriptions 1h 34m Pre-Recorded (Pre-Recorded v2)
Started Jul 07, 2026, 08:50 PM UTC· resolved Jul 07, 2026, 10:24 PM UTC
- investigating Jul 07, 2026, 08:50 PM UTC
There is a connectivity issue causing huge slow downs in transcriptions. We are working on identifying the root cause.
- monitoring Jul 07, 2026, 09:37 PM UTC
We've identified to the root cause. We are in recovery and monitoring the situation.
- resolved Jul 07, 2026, 10:24 PM UTC
The incident has been resolved. All pending jobs have been processed successfully.
Minor July 6, 2026 [Europe] Pre-Recorded is in a degraded state 3m
Started Jul 06, 2026, 08:25 PM UTC· resolved Jul 06, 2026, 08:28 PM UTC
- investigating Jul 06, 2026, 08:25 PM UTC
Service is unhealthy
- resolved Jul 06, 2026, 08:28 PM UTC
This incident has been resolved.
Minor July 3, 2026 Temporary Latency and Timeouts on Gladia API – Application (Website), Application (Add-ons), Application (Playground), Real-Time (Real-Time v2) and 3 more
Started Jul 03, 2026, 03:02 PM UTC· resolved Jul 03, 2026, 03:02 PM UTC
- resolved Jul 03, 2026, 03:02 PM 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 operating normally. We apologize for any disruption this may have caused.