Cartesia had 54 outages in the last 2 years totaling 50h 9m of downtime — averaging 2.2 incidents per month.
There were 54 Cartesia outages since October 14, 2025 totaling 50h 9m of downtime. Each is summarised below — incident details, duration, and resolution information.
The Playground is currently unavailable. API services are unaffected. We have identified the cause of the disruption and are actively working to remediate.
The Playground has been restored and is healthy. The disruption is resolved. API services were unaffected.
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.
The intermittent connectivity issues have resolved; we are continuing to monitor the state of our service.
This incident has been resolved.
The replacement for the offending change has been deployed. The incident is resolved.
Customers in the US regions are facing increased latency for some API requests.
Our caching service briefly experienced increased load due to the same configuration change, leading to increased latency in US regions again.
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.
This degradation has been quickly mitigated; we are closely monitoring performance for all key endpoints in the US regions.
We've identified an issue where new API keys result in an "Invalid API key" error.
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 incident.
Newly created API keys issued during this this period are invalid. Please create new API keys.
This incident has been resolved.
We are investigating the issue.
We have mitigated the issue on our end and are continuing to monitor the state of our service.
We have mitigated the issue on our end and are continuing to monitor the state of our service.
This incident has been resolved.
We are investigating the issue.
We are investigating the issue.
We have mitigated the issue on our end and are continuing to monitor the state of our service.
This incident has been resolved.
We are investigating some connection errors in US region.
We have mitigated the issue and continuing the root cause investigation.
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.
We are investigating the issue.
We have mitigated the issue on our end and are continuing to monitor the state of our service.
We have mitigated the issue on our end and are continuing to monitor the state of our service.
This incident has been resolved.
Degraded performance is observed in sonic-3 and sonic-3.5 in EU + US region, we are looking into the issue
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 `hi-IN`.
The change has been rollbacked in APAC.
We have mitigated the issue on our end and are continuing to monitor the state of our service.
This incident has been resolved.
Impacts voice agent background sounds and TTS history.
This incident has been resolved.
We're experiencing an elevated level of errors downloading files and are currently looking into the issue.
We are investigating the issue.
We are continuing to investigate the issue.
This incident has been resolved.
We have mitigated the issue on our end and are continuing to monitor the state of our service.
This incident has been resolved.
We are investigating the issue.
This incident has been resolved. We apologize for the inconvenience and will provide further details once we've concluded our internal investigation.
We are investigating the issue.
We are investigating the issue.
We have identified some network issues and are attempting to mitigate the issue.
Rerouting traffic
We have mitigated the issue on our end and are continuing to monitor the state of our service.
This incident has been resolved.
We are investigating the issue.
We have mitigated the issue on our end and are continuing to monitor the state of our service.
This incident has been resolved.
We are investigating the issue.
We have failed over to a backup provider and we're seeing recovery across the API.
We have mitigated the issue on our end and are continuing to monitor the state of our service.
This issue should be resolved now. We'll follow up with an RCA, but please reach out if you continue to see unexpected errors.
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.
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. We've also identified partial failures for some voice cloning requests and mitigated the issue.
We've mitigated this issue and customers should no longer see any degraded performance.
We are investigating an outage with our underlying infrastructure provider that impacted TTS / Agent traffic in the US.
We have mitigated the issue on our end and are continuing to monitor the state of our service.
We have mitigated the issue on our end and are continuing to monitor the state of our service.
This incident has been resolved.
Issue initiating new agent deployments via the CLI has been identified and a fix is being implemented. Calls are not impacted.
We have mitigated the issue on our end and are continuing to monitor the state of our service.
This incident has been resolved.
We are investigating the issue.
We have mitigated the issue on our end and are continuing to monitor the state of our service.
This incident has been resolved.
We are investigating the issue.
We have mitigated the issue on our end and are continuing to monitor the state of our service.
This incident has been resolved.
We are investigating the issue and what components are affected.
We have mitigated the issue on our end and are continuing to monitor the state of our service.
This incident has been resolved.
We are investigating the issue
A fix has been implemented and we are monitoring.
This incident has been resolved.
We are experiencing infrastructure issue with one of our infra provider, mainly impacting our voice clone feature in the US.
We are continuing to work on a fix for this issue.
We have mitigated the issue on our end and are continuing to monitor the state of our service.
This incident has been resolved.
There was a partial outage for ink-whisper due to which traffic being routed to a particular pod worker was failing. We have rolled out a fix for this to prevent this from happening again.