Cartesia Outage History

Cartesia is up right now

Pingoru has recorded 62 incidents for Cartesia: 56 in the last 12 months and 20 in the last 90 days.

Source: status.cartesia.ai

62incidents recorded
56last 12 months
20last 90 days
2 hourstypical duration
Incidents per month
0510AprMayJunJulAugSepOct5
Share of hours with an open incident, any severity
0%50%100%AprMayJunJulAugSepOct0%
Pingoru began tracking Cartesia in April 2026, so earlier months are not shown. Hover a bar for its value.
Show as a table
MonthIncidentsHours with an open incident
April 202632 of 720 (0%)
May 202669 of 744 (1%)
June 202698 of 720 (1%)
July 2026610 of 744 (1%)
August 202699 of 744 (1%)
September 2026426 of 720 (4%)
October 202652 of 548 (0%)

Incidents, newest first

Minor October 23, 2026 Elevated latency for instant voice cloning 1h 4m

Started Oct 23, 2026, 03:57 PM UTC· resolved Oct 23, 2026, 05:01 PM UTC

  1. identified Oct 23, 2026, 03:57 PM UTC

    Instant Voice Cloning latency is elevated, we are investigating.

  2. monitoring Oct 23, 2026, 04:26 PM UTC

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

  3. resolved Oct 23, 2026, 05:01 PM UTC

    This incident has been resolved.

Read the full incident report →

Minor October 22, 2026 Managed Agents with OpenAI LLMs may see degraded performance 9m

Started Oct 22, 2026, 03:13 AM UTC· resolved Oct 22, 2026, 03:23 AM UTC

  1. investigating Oct 22, 2026, 03:13 AM UTC

    We are investigating the issue and addressing with upstream provider.

  2. monitoring Oct 22, 2026, 03:19 AM UTC

    The issue seems to be [mitigated upstream](https://status.openai.com/incidents/01M5GPE9C4E19HE461P8JAMYXD) and we're continuing to monitor.

  3. resolved Oct 22, 2026, 03:23 AM UTC

    This incident has been resolved.

Read the full incident report →

Critical October 15, 2026 Playground unavailable 4m

Started Oct 15, 2026, 10:37 PM UTC· resolved Oct 15, 2026, 10:41 PM UTC

  1. identified Oct 15, 2026, 10:37 PM 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 Oct 15, 2026, 10:41 PM UTC

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

Read the full incident report →

Minor October 8, 2026 Intermittent API and Playground Errors 13m

Started Oct 08, 2026, 10:55 PM UTC· resolved Oct 08, 2026, 11:09 PM UTC

  1. investigating Oct 08, 2026, 10:55 PM 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 Oct 08, 2026, 11:06 PM UTC

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

  3. resolved Oct 08, 2026, 11:09 PM UTC

    This incident has been resolved.

Read the full incident report →

Major October 7, 2026 Degraded API Performance in US Regions –

Started Oct 07, 2026, 10:23 PM UTC· resolved Oct 07, 2026, 10:23 PM UTC

  1. resolved Oct 07, 2026, 11:17 PM UTC

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

  2. investigating Oct 07, 2026, 11:17 PM UTC

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

  3. investigating Oct 07, 2026, 11:17 PM UTC

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

  4. monitoring Oct 07, 2026, 11:17 PM 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.

  5. monitoring Oct 07, 2026, 11:17 PM UTC

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

Read the full incident report →

Notice September 23, 2026 API key issuing degraded 50m

Started Sep 23, 2026, 08:16 PM UTC· resolved Sep 23, 2026, 09:07 PM UTC

  1. investigating Sep 23, 2026, 08:16 PM UTC

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

  2. identified Sep 23, 2026, 08:26 PM 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 incident.

  3. identified Sep 23, 2026, 09:06 PM UTC

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

  4. resolved Sep 25, 2026, 11:47 PM UTC

    This incident has been resolved.

Read the full incident report →

Minor September 3, 2026 Intermittent issues with voice cloning in APAC 21h 3m

Started Sep 03, 2026, 10:34 PM UTC· resolved Sep 04, 2026, 07:37 PM UTC

  1. investigating Sep 03, 2026, 10:34 PM UTC

    We are investigating the issue.

  2. monitoring Sep 04, 2026, 03:53 AM UTC

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

  3. monitoring Sep 04, 2026, 03:53 AM UTC

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

  4. resolved Sep 04, 2026, 07:37 PM UTC

    This incident has been resolved.

Read the full incident report →

Minor September 3, 2026 Intermittent websocket connection throttling 3h 49m

Started Sep 03, 2026, 09:08 AM UTC· resolved Sep 03, 2026, 12:57 PM UTC

  1. investigating Sep 03, 2026, 09:08 AM UTC

    We are investigating the issue.

  2. investigating Sep 03, 2026, 09:26 AM UTC

    We are investigating the issue.

  3. monitoring Sep 03, 2026, 09:43 AM UTC

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

  4. resolved Sep 03, 2026, 12:57 PM UTC

    This incident has been resolved.

Read the full incident report →

Minor September 1, 2026 Elevated connection errors in US regions 3m

Started Sep 01, 2026, 08:00 PM UTC· resolved Sep 01, 2026, 08:04 PM UTC

  1. investigating Sep 01, 2026, 08:00 PM UTC

    We are investigating some connection errors in US region.

  2. resolved Sep 01, 2026, 08:04 PM UTC

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

  3. resolved Sep 02, 2026, 12:55 AM 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.

Read the full incident report →

Minor August 21, 2026 Elevated server-side TTFA for sonic-3.5 and sonic-3 in EU + US region 1h 27m

Started Aug 21, 2026, 12:06 PM UTC· resolved Aug 21, 2026, 01:33 PM UTC

  1. investigating Aug 21, 2026, 12:06 PM UTC

    We are investigating the issue.

  2. monitoring Aug 21, 2026, 12:37 PM UTC

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

  3. monitoring Aug 21, 2026, 01:00 PM UTC

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

  4. resolved Aug 21, 2026, 01:33 PM UTC

    This incident has been resolved.

Read the full incident report →

Notice August 21, 2026 Degraded performance in sonic-3.5 and sonic-3 46m

Started Aug 21, 2026, 11:59 AM UTC· resolved Aug 21, 2026, 12:45 PM UTC

  1. investigating Aug 21, 2026, 11:59 AM UTC

    Degraded performance is observed in sonic-3 and sonic-3.5 in EU + US region, we are looking into the issue

Read the full incident report →

Minor August 14, 2026 TTS language region validation fails requests 1h 36m

Started Aug 14, 2026, 07:58 AM UTC· resolved Aug 14, 2026, 09:34 AM UTC

  1. identified Aug 14, 2026, 07:58 AM 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 `hi-IN`.

  2. identified Aug 14, 2026, 08:07 AM UTC

    The change has been rollbacked in APAC.

  3. monitoring Aug 14, 2026, 09:31 AM UTC

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

  4. resolved Aug 14, 2026, 09:34 AM UTC

    This incident has been resolved.

Read the full incident report →

Minor August 14, 2026 Issues with files 1h 6m

Started Aug 14, 2026, 06:24 AM UTC· resolved Aug 14, 2026, 07:30 AM UTC

  1. identified Aug 14, 2026, 06:24 AM UTC

    Impacts voice agent background sounds and TTS history.

  2. resolved Aug 14, 2026, 07:30 AM UTC

    This incident has been resolved.

Read the full incident report →

Minor August 13, 2026 Elevated File Download Errors on TTS generations 1h 20m

Started Aug 13, 2026, 09:25 AM UTC· resolved Aug 13, 2026, 10:46 AM UTC

  1. investigating Aug 13, 2026, 09:25 AM UTC

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

  2. investigating Aug 13, 2026, 09:27 AM UTC

    We are investigating the issue.

  3. investigating Aug 13, 2026, 10:30 AM UTC

    We are continuing to investigate the issue.

  4. resolved Aug 13, 2026, 10:46 AM UTC

    This incident has been resolved.

  5. monitoring Aug 13, 2026, 10:47 AM UTC

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

  6. resolved Aug 13, 2026, 11:04 AM UTC

    This incident has been resolved.

Read the full incident report →

Major August 7, 2026 Agents Telephony failing in the US –

Started Aug 07, 2026, 03:20 PM UTC· resolved Aug 07, 2026, 03:20 PM UTC

  1. investigating Aug 07, 2026, 03:48 PM UTC

    We are investigating the issue.

  2. resolved Aug 07, 2026, 03:49 PM UTC

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

Read the full incident report →

Major August 5, 2026 Intermittent timeouts on TTS endpoints 1h 56m

Started Aug 05, 2026, 09:25 PM UTC· resolved Aug 05, 2026, 11:21 PM UTC

  1. investigating Aug 05, 2026, 09:25 PM UTC

    We are investigating the issue.

  2. investigating Aug 05, 2026, 09:36 PM UTC

    We are investigating the issue.

  3. investigating Aug 05, 2026, 09:43 PM UTC

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

  4. identified Aug 05, 2026, 09:45 PM UTC

    Rerouting traffic

  5. monitoring Aug 05, 2026, 09:50 PM UTC

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

  6. resolved Aug 05, 2026, 11:21 PM UTC

    This incident has been resolved.

Read the full incident report →

Major August 5, 2026 Intermittent PVC training errors 53m

Started Aug 05, 2026, 12:47 AM UTC· resolved Aug 05, 2026, 01:41 AM UTC

  1. identified Aug 05, 2026, 12:47 AM UTC

    We are investigating the issue.

  2. monitoring Aug 05, 2026, 01:07 AM UTC

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

  3. resolved Aug 05, 2026, 01:41 AM UTC

    This incident has been resolved.

Read the full incident report →

Major August 1, 2026 Elevated errors across the Cartesia API 51m

Started Aug 01, 2026, 01:40 AM UTC· resolved Aug 01, 2026, 02:31 AM UTC

  1. investigating Aug 01, 2026, 01:40 AM UTC

    We are investigating the issue.

  2. identified Aug 01, 2026, 01:47 AM UTC

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

  3. monitoring Aug 01, 2026, 01:53 AM UTC

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

  4. resolved Aug 01, 2026, 02:31 AM 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.

Read the full incident report →

Major July 30, 2026 Autoscaling performance investigation 6h 27m

Started Jul 30, 2026, 09:03 PM UTC· resolved Jul 31, 2026, 03:31 AM UTC

  1. investigating Jul 30, 2026, 09:03 PM 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 Jul 30, 2026, 11:31 PM 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. We've also identified partial failures for some voice cloning requests and mitigated the issue.

  3. resolved Jul 31, 2026, 02:31 AM UTC

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

Read the full incident report →

Major July 29, 2026 Partial TTS Outage in the US 21m

Started Jul 29, 2026, 10:17 PM UTC· resolved Jul 29, 2026, 10:39 PM UTC

  1. investigating Jul 29, 2026, 10:17 PM UTC

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

  2. monitoring Jul 29, 2026, 10:19 PM UTC

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

  3. monitoring Jul 29, 2026, 10:23 PM UTC

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

  4. resolved Jul 29, 2026, 10:39 PM UTC

    This incident has been resolved.

Read the full incident report →

Major July 22, 2026 Agent deployments via CLI are failing 1h 2m

Started Jul 22, 2026, 11:43 PM UTC· resolved Jul 23, 2026, 12:45 AM UTC

  1. identified Jul 22, 2026, 11:43 PM UTC

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

  2. monitoring Jul 23, 2026, 12:17 AM UTC

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

  3. resolved Jul 23, 2026, 12:45 AM UTC

    This incident has been resolved.

Read the full incident report →

Major July 21, 2026 Users are unable to login to the playground 1h 24m

Started Jul 21, 2026, 04:03 PM UTC· resolved Jul 21, 2026, 05:27 PM UTC

  1. investigating Jul 21, 2026, 04:03 PM UTC

    We are investigating the issue.

  2. monitoring Jul 21, 2026, 04:17 PM UTC

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

  3. resolved Jul 21, 2026, 05:27 PM UTC

    This incident has been resolved.

Read the full incident report →

Minor July 20, 2026 Sonic Latest Unavailable in EU region 17m

Started Jul 20, 2026, 05:51 PM UTC· resolved Jul 20, 2026, 06:09 PM UTC

  1. investigating Jul 20, 2026, 05:51 PM UTC

    We are investigating the issue.

  2. monitoring Jul 20, 2026, 06:01 PM UTC

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

  3. resolved Jul 20, 2026, 06:09 PM UTC

    This incident has been resolved.

Read the full incident report →

Critical July 17, 2026 Database read timeouts 23m

Started Jul 17, 2026, 08:13 PM UTC· resolved Jul 17, 2026, 08:36 PM UTC

  1. investigating Jul 17, 2026, 08:13 PM UTC

    We are investigating the issue and what components are affected.

  2. monitoring Jul 17, 2026, 08:29 PM UTC

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

  3. resolved Jul 17, 2026, 08:36 PM UTC

    This incident has been resolved.

Read the full incident report →

Major June 17, 2026 Errors with Line Agent Calls and Deployments 5m Voice Agents

Started Jun 17, 2026, 12:02 AM UTC· resolved Jun 17, 2026, 12:08 AM UTC

  1. investigating Jun 17, 2026, 12:02 AM UTC

    We are investigating the issue

  2. monitoring Jun 17, 2026, 12:06 AM UTC

    A fix has been implemented and we are monitoring.

  3. resolved Jun 17, 2026, 12:08 AM UTC

    This incident has been resolved.

Read the full incident report →