Cartesia

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 2026-10-15 22:37 UTC

   The Playground is currently unavailable. API services are unaffected. We have identified the cause of the disruption and are actively working to remediate.

2. resolved 2026-10-15 22:41 UTC

   The Playground has been restored and is healthy. The disruption is resolved. API services were unaffected.

Excerpts are shortened. Read the full incident on Cartesia'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. investigating 2026-10-08 22:55 UTC

   We are investigating intermittent errors affecting some API and Playground operations, including access-token creation, voice browsing, and agent management. We are working to identify the cause and mitigate.

2. monitoring 2026-10-08 23:06 UTC

   The intermittent connectivity issues have resolved; we are continuing to monitor the state of our service.

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

   This incident has been resolved.

Excerpts are shortened. Read the full incident on Cartesia'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. investigating 2026-10-07 16:29 UTC

   Customers in the US regions are facing increased latency for some API requests.

2. monitoring 2026-10-07 16:50 UTC

   The root cause has been identified as a change that led to increased load in our internal caching service. We have mitigated the issue on our end and are continuing to monitor the state of our service.

3. investigating 2026-10-07 21:13 UTC

   Our caching service briefly experienced increased load due to the same configuration change, leading to increased latency in US regions again.

4. monitoring 2026-10-07 21:16 UTC

   This degradation has been quickly mitigated; we are closely monitoring performance for all key endpoints in the US regions.

5. resolved 2026-10-07 22:23 UTC

   The replacement for the offending change has been deployed. The incident is resolved.

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

Failure mode: Login, tokens, certificates or credentials failed. Root cause: A bug in the vendor's own code. Tagged by claude-haiku-5-5 with high confidence (taxonomy v0.2).

1. investigating 2026-09-23 20:16 UTC

   We've identified an issue where new API keys result in an "Invalid API key" error.

2. identified 2026-09-23 20:26 UTC

   We've traced the issue to a bug in a change to our API key issuing logic that caused new keys to not be persisted correctly. The change is being reverted. Existing production traffic is not affected. We are exploring remediation options for API keys that were issued during the...

3. identified 2026-09-23 21:06 UTC

   Newly created API keys issued during this this period are invalid. Please create new API keys.

4. resolved 2026-09-23 21:07 UTC

   This incident has been resolved.

Excerpts are shortened. Read the full incident on Cartesia'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 2026-09-03 22:34 UTC

   We are investigating the issue.

2. monitoring 2026-09-04 03:53 UTC

   We have mitigated the issue on our end and are continuing to monitor the state of our service.

3. monitoring 2026-09-04 03:53 UTC

   We have mitigated the issue on our end and are continuing to monitor the state of our service.

4. resolved 2026-09-04 19:37 UTC

   This incident has been resolved.

Excerpts are shortened. Read the full incident on Cartesia'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 2026-09-03 09:08 UTC

   We are investigating the issue.

2. investigating 2026-09-03 09:26 UTC

   We are investigating the issue.

3. monitoring 2026-09-03 09:43 UTC

   We have mitigated the issue on our end and are continuing to monitor the state of our service.

4. resolved 2026-09-03 12:57 UTC

   This incident has been resolved.

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

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 2026-09-01 20:00 UTC

   We are investigating some connection errors in US region.

2. resolved 2026-09-01 20:04 UTC

   We have mitigated the issue and continuing the root cause investigation.

3. resolved 2026-09-02 00:55 UTC

   We have identified the root cause as upstream provider cluster maintenance that affected our service ingress. Some clients experienced connection errors, but subsequent retries were successful.

Excerpts are shortened. Read the full incident on Cartesia'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 2026-08-21 12:06 UTC

   We are investigating the issue.

2. monitoring 2026-08-21 12:37 UTC

   We have mitigated the issue on our end and are continuing to monitor the state of our service.

3. monitoring 2026-08-21 13:00 UTC

   We have mitigated the issue on our end and are continuing to monitor the state of our service.

4. resolved 2026-08-21 13:33 UTC

   This incident has been resolved.

Excerpts are shortened. Read the full incident on Cartesia'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. identified 2026-08-14 07:58 UTC

   A change rejects unknown TTS language regions, e.g. `hi-in` is rejected since an ISO 3166-1 alpha-2 country code is expected. We are working on rolling back this change. To correct the issue immediately, avoid sending the country code or send a corrected country code such as...

2. identified 2026-08-14 08:07 UTC

   The change has been rollbacked in APAC.

3. monitoring 2026-08-14 09:31 UTC

   We have mitigated the issue on our end and are continuing to monitor the state of our service.

4. resolved 2026-08-14 09:34 UTC

   This incident has been resolved.

Excerpts are shortened. Read the full incident on Cartesia'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. identified 2026-08-14 06:24 UTC

   Impacts voice agent background sounds and TTS history.

2. resolved 2026-08-14 07:30 UTC

   This incident has been resolved.

Excerpts are shortened. Read the full incident on Cartesia'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. investigating 2026-08-13 09:25 UTC

   We're experiencing an elevated level of errors downloading files and are currently looking into the issue.

2. investigating 2026-08-13 09:27 UTC

   We are investigating the issue.

3. investigating 2026-08-13 10:30 UTC

   We are continuing to investigate the issue.

4. resolved 2026-08-13 10:46 UTC

   This incident has been resolved.

5. monitoring 2026-08-13 10:47 UTC

   We have mitigated the issue on our end and are continuing to monitor the state of our service.

6. resolved 2026-08-13 11:04 UTC

   This incident has been resolved.

Excerpts are shortened. Read the full incident on Cartesia'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 2026-08-07 15:14 UTC

   We are investigating the issue.

2. resolved 2026-08-07 15:20 UTC

   This incident has been resolved. We apologize for the inconvenience and will provide further details once we've concluded our internal investigation.

Excerpts are shortened. Read the full incident on Cartesia'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 2026-08-05 21:25 UTC

   We are investigating the issue.

2. investigating 2026-08-05 21:36 UTC

   We are investigating the issue.

3. investigating 2026-08-05 21:43 UTC

   We have identified some network issues and are attempting to mitigate the issue.

4. identified 2026-08-05 21:45 UTC

   Rerouting traffic

5. monitoring 2026-08-05 21:50 UTC

   We have mitigated the issue on our end and are continuing to monitor the state of our service.

6. resolved 2026-08-05 23:21 UTC

   This incident has been resolved.

Excerpts are shortened. Read the full incident on Cartesia'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 2026-08-05 00:15 UTC

   We are investigating the issue.

2. monitoring 2026-08-05 01:07 UTC

   We have mitigated the issue on our end and are continuing to monitor the state of our service.

3. resolved 2026-08-05 01:41 UTC

   This incident has been resolved.

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

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 2026-08-01 01:33 UTC

   We are investigating the issue.

2. identified 2026-08-01 01:47 UTC

   We have failed over to a backup provider and we're seeing recovery across the API.

3. monitoring 2026-08-01 01:50 UTC

   We have mitigated the issue on our end and are continuing to monitor the state of our service.

4. resolved 2026-08-01 02:31 UTC

   This issue should be resolved now. We'll follow up with an RCA, but please reach out if you continue to see unexpected errors.

Excerpts are shortened. Read the full incident on Cartesia'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 2026-07-30 21:03 UTC

   We’re investigating an issue affecting autoscaling performance. Services remain available, though some customers may experience temporary degradation in quality. Our team is actively working to identify and mitigate the issue, and we’ll provide updates as they become available.

2. investigating 2026-07-30 23:31 UTC

   We’re investigating an issue affecting autoscaling performance. Services remain available, though some customers may experience temporary degradation in quality. Our team is actively working to identify and mitigate the issue, and we’ll provide updates as they become available....

3. resolved 2026-07-31 03:31 UTC

   We've mitigated this issue and customers should no longer see any degraded performance.

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

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 2026-07-29 21:58 UTC

   We are investigating an outage with our underlying infrastructure provider that impacted TTS traffic in the US.

2. monitoring 2026-07-29 22:19 UTC

   We have mitigated the issue on our end and are continuing to monitor the state of our service.

3. monitoring 2026-07-29 22:23 UTC

   We have mitigated the issue on our end and are continuing to monitor the state of our service.

4. resolved 2026-07-29 22:39 UTC

   This incident has been resolved.

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

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 medium confidence (taxonomy v0.2).

1. identified 2026-07-22 23:43 UTC

   Issue initiating new agent deployments via the CLI has been identified and a fix is being implemented. Calls are not impacted.

2. monitoring 2026-07-23 00:17 UTC

   We have mitigated the issue on our end and are continuing to monitor the state of our service.

3. resolved 2026-07-23 00:45 UTC

   This incident has been resolved.

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

Failure mode: Login, tokens, certificates or credentials failed. Root cause: The vendor does not say why it happened. Tagged by claude-haiku-5-5 with medium confidence (taxonomy v0.2).

1. investigating 2026-07-21 16:03 UTC

   We are investigating the issue.

2. monitoring 2026-07-21 16:17 UTC

   We have mitigated the issue on our end and are continuing to monitor the state of our service.

3. resolved 2026-07-21 17:27 UTC

   This incident has been resolved.

Excerpts are shortened. Read the full incident on Cartesia'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. investigating 2026-07-20 17:51 UTC

   We are investigating the issue.

2. monitoring 2026-07-20 18:01 UTC

   We have mitigated the issue on our end and are continuing to monitor the state of our service.

3. resolved 2026-07-20 18:09 UTC

   This incident has been resolved.

Excerpts are shortened. Read the full incident on Cartesia'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. investigating 2026-07-17 20:13 UTC

   We are investigating the issue and what components are affected.

2. monitoring 2026-07-17 20:29 UTC

   We have mitigated the issue on our end and are continuing to monitor the state of our service.

3. resolved 2026-07-17 20:36 UTC

   This incident has been resolved.

Excerpts are shortened. Read the full incident on Cartesia'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. monitoring 2024-07-17 17:33 UTC

   Let your users know once a fix is in place, and keep communication clear and precise.

2. identified 2024-07-17 17:39 UTC

   As you continue to work through the incident, update your customers frequently.

3. resolved 2024-07-17 17:43 UTC

   Empathize with those affected and let them know everything is operating as normal.

4. investigating 2024-07-17 18:09 UTC

   When your product or service isn’t functioning as expected, let your customers know by creating an incident. Communicate early, even if you don’t know exactly what’s going on.

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

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 2024-07-25 13:23 UTC

   A recent deploy has caused some users to report issues with voice cloning. We are currently investigating

2. monitoring 2024-07-25 13:44 UTC

   A fix has been deployed, tests in production look good waiting for user feedback.

3. resolved 2024-07-25 13:48 UTC

   Confirmed the deployed fix works as intended. Reported user issues have been resolved.

Excerpts are shortened. Read the full incident on Cartesia'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 2024-07-25 13:30 UTC

   Cartesia server was down for ~8-10 minutes

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

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. identified 2024-07-24 20:53 UTC

   The Playground is currently down for a subsection of users. We've identified the issue and are rolling back the change.

2. monitoring 2024-07-24 21:07 UTC

   Fix has been deployed, validated on a few test accounts and waiting for user feedback.

3. resolved 2024-07-24 21:22 UTC

   Incident's been resolved.

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