- Detected by Pingoru
- Feb 09, 2026, 05:05 PM UTC
- Resolved
- Feb 09, 2026, 06:00 PM UTC
- Duration
- 55m
Affected: Text to Speech (APAC)
Timeline · 3 updates
-
investigating Feb 09, 2026, 05:16 PM UTC
We've noticed errors when generating audio on `/bytes` and `/sse` endpoints in India. We are currently investigating this issue.
-
monitoring Feb 09, 2026, 05:55 PM UTC
We've identified and mitigated a DDoS attack on our APAC infrastructure. Traffic protection measures are now in place and routing has been restored. We're continuing to monitor the situation to ensure stability. Error rates have been normalized.
-
resolved Feb 09, 2026, 06:00 PM UTC
This incident has been resolved.
Read the full incident report →
- Detected by Pingoru
- Dec 18, 2025, 07:48 PM UTC
- Resolved
- Dec 18, 2025, 08:10 PM UTC
- Duration
- 22m
Affected: Text to Speech (US)
Timeline · 4 updates
-
identified Dec 18, 2025, 07:48 PM UTC
A faulty deploy temporarily took down our TTS on the US cluster. Traffic rerouted to backup clusters and auto rollback for US fired but there was a spike in 503 errors briefly. Looking into confirming this has been resolved
-
monitoring Dec 18, 2025, 07:49 PM UTC
Healthchecks indicate this is currently working as intended, will continue to monitor for a bit before closing
-
resolved Dec 18, 2025, 08:10 PM UTC
Confirmed there are no longer any issues. Users likely saw a brief spike in 503s, and then elevated TTFAs (backup cluster) for a few minutes, entire incident would have resolved in a few minutes. Will have an RCA shortly
-
postmortem Dec 18, 2025, 08:10 PM UTC
We had a faulty deploy to the US cluster that would have resulted in a brief spike in 503s. Newer traffic was rerouted to our backup cluster \(EU\) while rollback initiated in the US which took a minute\*.
Read the full incident report →
Critical November 14, 2025 - Detected by Pingoru
- Nov 14, 2025, 02:29 AM UTC
- Resolved
- Nov 14, 2025, 03:03 AM UTC
- Duration
- 33m
Affected: Playground
Timeline · 2 updates
-
investigating Nov 14, 2025, 02:29 AM UTC
The Cartesia playground is currently down. We are investigating.
-
resolved Nov 14, 2025, 03:03 AM UTC
The playground should be back up. The playground outage was downstream of a more general outage on CRUD endpoints caused by a database issue which is now resolved. Thanks to previous infra hardening efforts, this issue did not affect production traffic on our real-time APIs, including TTS & STT.
Read the full incident report →
- Detected by Pingoru
- Nov 10, 2025, 07:53 AM UTC
- Resolved
- Nov 10, 2025, 08:04 AM UTC
- Duration
- 11m
Affected: Text to Speech (EU)
Timeline · 5 updates
-
identified Nov 10, 2025, 07:53 AM UTC
As part of a scheduled node migration, the EU specific domain was routed to a new node. This appears to not be working as intended, we're deploying a fix shortly.
-
monitoring Nov 10, 2025, 07:55 AM UTC
We've deployed a fix for the route.
-
monitoring Nov 10, 2025, 07:58 AM UTC
We are continuing to monitor for any further issues.
-
resolved Nov 10, 2025, 08:04 AM UTC
Users appear to confirm that this has been resolved since. Will update retroactively with a more thorough RCA.
-
postmortem Nov 10, 2025, 08:34 AM UTC
We had a scheduled node migration during this timeframe that was intended to be a no-op. The intermediary cluster to which the `api-eu` domain specifically was routed to was not expected to affect, but unfortunately the `api-eu` was not properly whitelisted. This was a gap in our health checks that we did not catch this immediately and rollback, we'll be updating that in our pipeline. The primary `api` route with geosteering was unaffected, even if called from the EU domain.
Read the full incident report →
- Detected by Pingoru
- Nov 06, 2025, 07:16 PM UTC
- Resolved
- Nov 06, 2025, 07:38 PM UTC
- Duration
- 22m
Affected: Playground
Timeline · 3 updates
-
investigating Nov 06, 2025, 07:16 PM UTC
We are experiencing some database connection issues impacting some product service area including Agents and Narrations. These do not impact TTS, Voice or Cloning APIs.
-
monitoring Nov 06, 2025, 07:38 PM UTC
Root cause was determined to be an unforeseen networking configuration change from an upstream provider. Mitigations have been applied, all errors are resolved, and we’re closely monitoring the system.
-
resolved Nov 06, 2025, 07:38 PM UTC
This incident has been resolved.
Read the full incident report →
- Detected by Pingoru
- Nov 04, 2025, 07:52 PM UTC
- Resolved
- Nov 05, 2025, 08:49 PM UTC
- Duration
- 1d
Affected: Voice Cloning
Timeline · 4 updates
-
investigating Nov 04, 2025, 07:52 PM UTC
Pro Voice Cloning is experiencing some hangs in the training pipeline. We are investigating into the root cause of PVCs being stuck and not reaching completion or failure.
-
investigating Nov 04, 2025, 09:44 PM UTC
We found a serialization issue that is causing uncaught errors in our training pipeline. We are working on a fix for both the serialization bug and improved error handling to communicate failed training pipelines to users.
-
identified Nov 05, 2025, 02:49 AM UTC
We have identified the root cause. The issue is impacting only a small number of requests and we are providing support for users. The full resolution will be resolved in the next Morning to ensure stability of our other services.
-
resolved Nov 05, 2025, 08:49 PM UTC
This incident has been resolved.
Read the full incident report →
- Detected by Pingoru
- Oct 14, 2025, 08:47 PM UTC
- Resolved
- Oct 14, 2025, 11:17 PM UTC
- Duration
- 2h 29m
Affected: Text to Speech (US)Speech to Text (US)
Timeline · 8 updates
Read the full incident report →
- Detected by Pingoru
- Oct 07, 2025, 04:54 PM UTC
- Resolved
- Oct 07, 2025, 06:32 PM UTC
- Duration
- 1h 38m
Affected: Text to Speech (US)
Timeline · 6 updates
-
investigating Oct 07, 2025, 04:54 PM UTC
We are currently investigating reported instability in our TTS API in the US cluster
-
investigating Oct 07, 2025, 04:57 PM UTC
Currently investigating if this is related to Cloudflare KV issues (https://www.cloudflarestatus.com/incidents/ff4947s38tlb)
-
monitoring Oct 07, 2025, 05:54 PM UTC
The timeout errors have recovered, but we're continuing to monitor on our end. The aforementioned Cloudflare incident (https://www.cloudflarestatus.com/incidents/ff4947s38tlb) has been mitigated as well.
-
monitoring Oct 07, 2025, 06:03 PM UTC
We've confirmed that this is cloudflare related, they've introduced mitigations (see here https://www.cloudflarestatus.com/incidents/ff4947s38tlb) and this appears to have resolved issues. Monitoring now
-
monitoring Oct 07, 2025, 06:03 PM UTC
We are continuing to monitor for any further issues.
-
resolved Oct 07, 2025, 06:32 PM UTC
This incident has been resolved.
Read the full incident report →
- Detected by Pingoru
- Oct 01, 2025, 06:26 PM UTC
- Resolved
- Oct 01, 2025, 09:05 PM UTC
- Duration
- 2h 39m
Affected: Voice Cloning
Timeline · 4 updates
-
investigating Oct 01, 2025, 06:26 PM UTC
We are experiencing an issue where all PVC creations are failing. We are actively looking into this issue.
-
identified Oct 01, 2025, 06:42 PM UTC
We've identified the issue and are currently testing a hotfix.
-
monitoring Oct 01, 2025, 08:13 PM UTC
We've implemented a fix to the pipeline, and we're actively monitoring. Users can re-try any failed Pro Voice Clones to re-train them.
-
resolved Oct 01, 2025, 09:05 PM UTC
This incident has been resolved.
Read the full incident report →
- Detected by Pingoru
- Sep 18, 2025, 01:00 PM UTC
- Resolved
- Sep 18, 2025, 01:00 PM UTC
- Duration
- —
Timeline · 1 update
-
resolved Sep 18, 2025, 01:54 PM UTC
A recent deployment introduced regressions affecting a subset of text-to-speech (TTS) requests using the latest sonic-2 model ID, including the dated variants sonic-2-2025-05-08 and sonic-2-2025-06-11. Between 1:00–1:30 pm UTC, impacted requests experienced elevated API error rates. The issue was isolated to the affected model IDs and did not impact other TTS models. The incident has been resolved.
Read the full incident report →
- Detected by Pingoru
- Sep 17, 2025, 10:06 PM UTC
- Resolved
- Sep 18, 2025, 03:44 AM UTC
- Duration
- 5h 37m
Affected: Playground
Timeline · 2 updates
-
investigating Sep 17, 2025, 10:06 PM UTC
We are currently investigating export failures in Narrations.
-
resolved Sep 18, 2025, 03:44 AM UTC
This incident, which was caused by an inconsistency in how the Bun JS runtime handles multipart file uploads containing JS Blob objects, has been resolved.
Read the full incident report →
- Detected by Pingoru
- Sep 17, 2025, 07:22 AM UTC
- Resolved
- Sep 17, 2025, 08:44 PM UTC
- Duration
- 13h 21m
Affected: Playground
Timeline · 2 updates
-
identified Sep 17, 2025, 07:22 AM UTC
Playground sign-in/sign-up is currently degraded due to an outage in our auth provider, Clerk. For updates, see status.clerk.com.
-
resolved Sep 17, 2025, 08:44 PM UTC
This incident has been resolved.
Read the full incident report →
- Detected by Pingoru
- Sep 04, 2025, 08:10 PM UTC
- Resolved
- Sep 04, 2025, 08:44 PM UTC
- Duration
- 34m
Affected: Text to Speech (US)Speech to Text (US)Playground
Timeline · 4 updates
-
investigating Sep 04, 2025, 08:10 PM UTC
We are currently investigating this issue.
-
investigating Sep 04, 2025, 08:21 PM UTC
We've put a mitigation in place and traffic is coming back to the cluster. We're continuing to monitor.
-
investigating Sep 04, 2025, 08:39 PM UTC
All NA cluster traffic has stabilized. We continue to monitor and will share the upstream provider’s RCA on the network instability. We'll put appropriate mitigations in place once we have this update.
-
resolved Sep 04, 2025, 08:44 PM UTC
This incident has been resolved.
Read the full incident report →
- Detected by Pingoru
- Aug 25, 2025, 01:00 AM UTC
- Resolved
- Aug 25, 2025, 01:00 AM UTC
- Duration
- —
Timeline · 1 update
-
resolved Aug 25, 2025, 01:45 AM UTC
Between 6:04:56 PM and 6:05:36 PM PDT (40 second period) on Aug 24th 2025, our NA cluster experienced instability due to a networking problem from an upstream provider. This caused 503 errors on new requests and WebSocket connections for TTS and STT traffic in North America.
Read the full incident report →
- Detected by Pingoru
- Aug 21, 2025, 07:07 PM UTC
- Resolved
- Aug 21, 2025, 08:04 PM UTC
- Duration
- 57m
Affected: Text to Speech (US)
Timeline · 3 updates
-
identified Aug 21, 2025, 07:07 PM UTC
https://www.cloudflarestatus.com/ Cloudflare is experiencing an outage in IAD that has impacted network performance leading to instability with requests in our US East region. We're continuing to monitor.
-
identified Aug 21, 2025, 08:04 PM UTC
We are continuing to work on a fix for this issue.
-
resolved Aug 21, 2025, 08:04 PM UTC
This incident has been resolved.
Read the full incident report →
- Detected by Pingoru
- Aug 15, 2025, 01:57 PM UTC
- Resolved
- Aug 15, 2025, 01:59 PM UTC
- Duration
- 1m
Affected: Text to Speech (US)Speech to Text (US)
Timeline · 2 updates
-
monitoring Aug 15, 2025, 01:57 PM UTC
Between 6:40 am PT -> 6:43 am PT, we observed degraded performance in the US cluster. All systems are operational now. We are monitoring.
-
resolved Aug 15, 2025, 01:59 PM UTC
This incident has been resolved. Our cluster provider had a network outage and has recovered. We are monitoring the cluster and working with the provider to RCA the issue.
Read the full incident report →
- Detected by Pingoru
- Aug 11, 2025, 05:45 PM UTC
- Resolved
- Aug 11, 2025, 05:45 PM UTC
- Duration
- —
Affected: Text to Speech (US)
Timeline · 1 update
-
resolved Aug 11, 2025, 05:45 PM UTC
We noticed a spike in load in the EU, which may have caused elevated latencies briefly. Our alerting system flagged this spike and we scaled our EU cluster to handle it. Latencies should be back to normal.
Read the full incident report →
- Detected by Pingoru
- Jul 24, 2025, 06:03 PM UTC
- Resolved
- Jul 24, 2025, 09:32 PM UTC
- Duration
- 3h 28m
Affected: Text to Speech (US)
Timeline · 4 updates
-
investigating Jul 24, 2025, 06:03 PM UTC
We're seeing reports of latency spikes from our NA cluster in short periods of time, and we're actively investigating. Appeared around 10:20 and 10:45 am PT
-
identified Jul 24, 2025, 06:44 PM UTC
We haven't had a latency spike in a while but we're sporadically seeing workers be unavailable, reducing our capacity. Spinning up a new cluster to swap over to in order to reset the state of our nodes.
-
monitoring Jul 24, 2025, 08:34 PM UTC
We've rolled over 100% of traffic to the new cluster. Monitoring now
-
resolved Jul 24, 2025, 09:32 PM UTC
Seems we've been fine for an hour, closing. RCA coming shortly
Read the full incident report →
- Detected by Pingoru
- Jul 21, 2025, 09:18 AM UTC
- Resolved
- Jul 21, 2025, 09:44 PM UTC
- Duration
- 12h 25m
Affected: Text to Speech (US)
Timeline · 9 updates
Read the full incident report →
- Detected by Pingoru
- Jul 21, 2025, 04:44 AM UTC
- Resolved
- Jul 21, 2025, 08:33 AM UTC
- Duration
- 3h 49m
Affected: Text to Speech (US)
Timeline · 6 updates
-
investigating Jul 21, 2025, 04:44 AM UTC
We are currently experiencing some instability in our EU cluster. We're going to begin rolling traffic over to the NA cluster while we investigate the degradation.
-
monitoring Jul 21, 2025, 06:28 AM UTC
EU cluster is back up and appears to be stable. Continuing to monitor
-
identified Jul 21, 2025, 07:21 AM UTC
It seems the mitigation we put in place for the EU cluster didn't hold. We're going to be rerouting EU traffic back to NA for the time being while we do a full rollback.
-
monitoring Jul 21, 2025, 08:21 AM UTC
We've completed the full rollback and routed EU traffic back to the EU cluster. Will continue monitoring
-
monitoring Jul 21, 2025, 08:21 AM UTC
We are continuing to monitor for any further issues.
-
resolved Jul 21, 2025, 08:33 AM UTC
EU Cluster is stabilized.
Read the full incident report →
- Detected by Pingoru
- Jul 18, 2025, 03:24 AM UTC
- Resolved
- Jul 18, 2025, 05:07 AM UTC
- Duration
- 1h 43m
Affected: Text to Speech (US)
Timeline · 4 updates
-
identified Jul 18, 2025, 03:24 AM UTC
A few bad workers have introduced some temporary latency to our APAC cluster. We are rolling them back now.
-
monitoring Jul 18, 2025, 04:12 AM UTC
A fix has been implemented and we are monitoring the results.
-
monitoring Jul 18, 2025, 04:12 AM UTC
We are continuing to monitor for any further issues.
-
resolved Jul 18, 2025, 05:07 AM UTC
This incident has been resolved.
Read the full incident report →
- Detected by Pingoru
- Jun 26, 2025, 06:27 AM UTC
- Resolved
- Jun 26, 2025, 07:22 AM UTC
- Duration
- 54m
Affected: Playground
Timeline · 2 updates
-
investigating Jun 26, 2025, 06:27 AM UTC
Our playground auth provider, Clerk, is experiencing an outage. Playground is currently inaccessible.
-
resolved Jun 26, 2025, 07:22 AM UTC
This incident has been resolved.
Read the full incident report →
- Detected by Pingoru
- Jun 11, 2025, 07:44 AM UTC
- Resolved
- Jun 11, 2025, 10:13 AM UTC
- Duration
- 2h 29m
Affected: Text to Speech (US)PlaygroundVoice Cloning
Timeline · 2 updates
-
investigating Jun 11, 2025, 07:44 AM UTC
Some of our US region servers are down, causing requests to fail over to other regions, with higher latency.
-
resolved Jun 11, 2025, 10:13 AM UTC
We root-caused the issue to a networking problem from an upstream provider, which has been resolved.
Read the full incident report →
- Detected by Pingoru
- Jun 09, 2025, 08:11 PM UTC
- Resolved
- Jun 09, 2025, 09:08 PM UTC
- Duration
- 57m
Affected: Text to Speech (US)
Timeline · 4 updates
-
investigating Jun 09, 2025, 08:11 PM UTC
Some API users are experiencing errors with concurrency limits.
-
investigating Jun 09, 2025, 08:29 PM UTC
We are continuing to investigate this issue.
-
investigating Jun 09, 2025, 09:08 PM UTC
We are continuing to investigate this issue.
-
resolved Jun 09, 2025, 09:08 PM UTC
This incident has been resolved.
Read the full incident report →
