outages.live
Live
C

Cartesia

Cartesia is operational

Checked 3 min ago Operational

History

90 days agoToday

Incidents in 90 days

14

Days with an incident

12

Median duration

1 h 5 min

Longest incident

21 h 4 min

Components

11
Text to Speech (US) Operational
90 days agoNo incidentsToday
Text to Speech (EU) Operational
90 days agoNo incidentsToday
Text to Speech (APAC) Operational
90 days agoNo incidentsToday
Text to Speech (AU) Operational
90 days agoNo incidentsToday
Speech to Text (US) Operational
90 days agoNo incidentsToday
Speech to Text (EU) Operational
90 days agoNo incidentsToday
Speech to Text (APAC) Operational
90 days agoNo incidentsToday
Speech to Text (AU) Operational
90 days agoNo incidentsToday
Playground Operational
90 days agoNo incidentsToday
Voice Cloning Operational
90 days agoNo incidentsToday
Voice Agents Operational
90 days agoNo incidentsToday

Past incidents

Provider status pageTimes in UTC

Oct 23, 2026

Duration1 h 4 min15:57 to 17:01Elevated latency for instant voice cloningDegraded

This incident has been resolved.

Oct 22, 2026

Duration10 min03:13 to 03:23Managed Agents with OpenAI LLMs may see degraded performanceDegraded

This incident has been resolved.

Oct 15, 2026

Duration4 min22:37 to 22:41Playground unavailableMajor outage

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

Oct 8, 2026

Duration14 min22:55 to 23:09Intermittent API and Playground ErrorsDegraded

This incident has been resolved.

Sep 23, 2026

Duration50 min20:16 to 21:07API key issuing degradedNotice

This incident has been resolved.

Sep 3, 2026

Duration21 h 4 min22:34 to 19:37Intermittent issues with voice cloning in APACDegraded

This incident has been resolved.

Duration3 h 49 min09:08 to 12:57Intermittent websocket connection throttlingDegraded

This incident has been resolved.

Sep 1, 2026

Duration3 min20:00 to 20:04Elevated connection errors in US regionsDegraded

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.

Aug 21, 2026

Duration1 h 28 min12:06 to 13:33Elevated server-side TTFA for sonic-3.5 and sonic-3 in EU + US regionDegraded

This incident has been resolved.

Aug 14, 2026

Duration1 h 37 min07:58 to 09:34TTS language region validation fails requestsDegraded

This incident has been resolved.

Duration1 h 7 min06:24 to 07:30Issues with filesDegraded

This incident has been resolved.

Aug 13, 2026

Duration1 h 21 min09:25 to 10:46Elevated File Download Errors on TTS generationsDegraded

This incident has been resolved.

Aug 5, 2026

Duration1 h 56 min21:25 to 23:21Intermittent timeouts on TTS endpointsPartial outage

This incident has been resolved.

Duration54 min00:47 to 01:41Intermittent PVC training errorsPartial outage

This incident has been resolved.

Follow Cartesia

Your coding agent knows when Cartesia is down, and tells you when a failure is theirs, not yours. You can also get Cartesia incidents in a feed reader or in Slack.

Prompt
Install the outages.live MCP server, so that when something breaks you can tell if the cause is a provider we depend on and not my code. It reads the official status pages of cloud, AI, payment and developer providers and gives you their incidents as MCP tools.

Add it as a remote MCP server named "outages" at https://outages.cc/mcp (Streamable HTTP, no authentication), with your CLI command or your MCP config file.

Then:
1. Make sure it connects and shows the tools get_provider, list_feed and send_feedback.
2. Call get_provider with "cartesia" and tell me if Cartesia has a problem right now.
3. From now on, when a call to a third-party service fails or becomes slow, call get_provider for that service before you change my code.

Paste this into any coding agent. It adds the server with its own MCP setup.

RSS
https://outages.cc/feed.xml?providers=cartesia
Slack
/feed subscribe https://outages.cc/feed.xml?providers=cartesia

Go from tracking outages to fixing production issues with Polylane.

Try Polylane