Cartesia Outage History

45 incidents recorded over the last 365 days, 45 of them resolved. Durations are measured from when PulsAPI first saw the problem to when it cleared, which is usually longer than the vendor's own figure.

Live Cartesia status100.00% uptime history

Every Recorded Cartesia Incident

Cartesia incidents, newest first, with date, duration and status.
DateIncidentDurationStatus
Oct 23, 2026Elevated latency for instant voice cloningThis incident has been resolved.1h 4mResolved
Oct 22, 2026Managed Agents with OpenAI LLMs may see degraded performanceThis incident has been resolved.9 minResolved
Oct 15, 2026Playground unavailableThe Playground has been restored and is healthy. The disruption is resolved. API services were unaffected.4 minResolved
Oct 8, 2026Intermittent API and Playground ErrorsThis incident has been resolved.13 minResolved
Oct 7, 2026Degraded API Performance in US RegionsThe replacement for the offending change has been deployed. The incident is resolved.-54 minResolved
Sep 23, 2026API key issuing degradedThis incident has been resolved.50 minResolved
Sep 21, 2026Scheduled Maintenance on Playground Sign-In/Sign-UpScheduled maintenance is currently in progress. Users may have issues generating TTS responses or calling agents through the Playground. API usage is unaffected.9h 19mResolved
Sep 10, 2026Cluster maintenance in EU regionMaintenance has started196h 17mResolved
Sep 10, 2026Cluster maintenance in AP regionMaintenance has started196h 52mResolved
Sep 3, 2026Intermittent issues with voice cloning in APACThis incident has been resolved.21h 3mResolved
Sep 3, 2026Intermittent websocket connection throttlingThis incident has been resolved.3h 49mResolved
Sep 1, 2026Elevated connection errors in US regionsWe 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.3 minResolved
Aug 28, 2026Cluster maintenance in US regionMaintenance has started198h 31mResolved
Aug 28, 2026Cluster maintenance in EU regionMaintenance has started198h 33mResolved
Aug 21, 2026Elevated server-side TTFA for sonic-3.5 and sonic-3 in EU + US regionThis incident has been resolved.1h 27mResolved
Aug 21, 2026Degraded performance in sonic-3.5 and sonic-3We have mitigated the issue on our end and are continuing to monitor the state of our service.38 minResolved
Aug 18, 2026Cluster maintenance in AU regionMaintenance has started159h 40mResolved
Aug 14, 2026TTS language region validation fails requestsThis incident has been resolved.1h 36mResolved
Aug 14, 2026Issues with filesThis incident has been resolved.1h 6mResolved
Aug 13, 2026Elevated File Download Errors on TTS generationsThis incident has been resolved.1h 20mResolved
Aug 7, 2026Agents Telephony failing in the USThis incident has been resolved. We apologize for the inconvenience and will provide further details once we've concluded our internal investigation.-28 minResolved
Aug 5, 2026Intermittent timeouts on TTS endpointsThis incident has been resolved.1h 56mResolved
Aug 5, 2026Intermittent PVC training errorsThis incident has been resolved.53 minResolved
Aug 1, 2026Elevated errors across the Cartesia APIThis issue should be resolved now. We'll follow up with an RCA, but please reach out if you continue to see unexpected errors.51 minResolved
Jul 30, 2026Autoscaling performance investigationWe've mitigated this issue and customers should no longer see any degraded performance.6h 27mResolved
Jul 29, 2026Partial TTS Outage in the USThis incident has been resolved.21 minResolved
Jul 22, 2026Agent deployments via CLI are failingThis incident has been resolved.1h 2mResolved
Jul 21, 2026Users are unable to login to the playgroundThis incident has been resolved.1h 24mResolved
Jul 20, 2026Sonic Latest Unavailable in EU regionThis incident has been resolved.17 minResolved
Jul 17, 2026Database read timeoutsThis incident has been resolved.23 minResolved
Jul 10, 2026This is an example incidentWhen 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.-1041092 minResolved
Jul 10, 2026Corrupt WorkerOne of our workers was corrupted for 20-30 minutes, so a small increase in voice generation issues there.-1002165 minResolved
Jul 10, 2026Production API OutageRoot cause was identified. Solution has been working for the last ~4-5 hours so marking this as resolved.-1007617 minResolved
Jul 10, 2026Vercel OutageThis incident has been resolved.-1010721 minResolved
Jul 10, 2026Voice Cloning IssuesConfirmed the deployed fix works as intended. Reported user issues have been resolved.-1029807 minResolved
Jul 10, 2026API Server DownCartesia server was down for ~8-10 minutes-1029825 minResolved
Jul 10, 2026Playground DownIncident's been resolved.-1030792 minResolved
Jul 10, 2026500 errors on TTS requests with timestampsOur API was returning 500s on some requests, eventually at 100% outage for a period of 30 minutes on all requests with add_timestamps.-902895 minResolved
Jul 10, 2026API Server DownRoot cause identified and full fix deployed to production. Post mortem to be shared out soon.-1000507 minResolved
Jul 10, 2026TTS InstabilityFix was deployed to production from staging and confirmed as valid in production.-881095 minResolved
Jul 10, 2026API down due to Together outageOur infrastructure provider had unscheduled maintenance from its data center. This caused our nodes to be "_down for a firmware update without \[their\] approval._" Our engagement with this provider requires explicit…-899955 minResolved
Jul 10, 2026Voice Cloning InstabilityBug in a deployment was identified and rolled back.-869529 minResolved
Jul 10, 2026WebSocket connection issuesThis incident has been resolved.-830235 minResolved
Jul 10, 2026Data inconsistency issues due to accidental DB switchThis incident has been resolved.-830411 minResolved
Jul 10, 2026Websocket IssuesThe data center Together AI used to house our cluster experienced Internet Bandwidth issues. Per the RCA we received from Together: On 12 November at 11:36 \(all times Eastern\), Flexential received reports from…-871066 minResolved

Hear about the next one while it is open

Everything above is a record written after the fact. We can email you when the next Cartesia incident opens instead, at the point where knowing still changes what you do.

Free, no password, no card. Unsubscribe in one click.

How to Read This Cartesia Incident Log

Each row is an incident PulsAPI observed, not a summary written afterwards. The duration is wall-clock time between the first failing check and the first clean one, so it includes the window before Cartesia acknowledged anything. Vendor post-mortems typically measure from acknowledgement, which is why their numbers are usually shorter.

Incidents still open have no duration yet and are listed as ongoing rather than being given a running total. The archive covers the last 365 days; anything older has aged out of the window rather than never having happened.

The longest single Cartesia outage in this window ran 8d 6h, against a mean recovery of 1d 11h. If you depend on Cartesia in a customer-facing path, the longest figure is the one to design around. The mean is what happens on a normal bad day; the maximum is what happens on the worst one.