outages.live
Live
CartesiaIncident · 2026-09-23 20:16 UTC

API key issuing degraded

ResolvedOfficial update

This incident has been resolved.

The latest update from Cartesia.

State

Resolved

Started

39 d ago

2026-09-23 20:16 UTC

Lasted

50 min

until 2026-09-23 21:07 UTC

Worst impact

Notice

Timeline

4 updates
20:1620:2920:4120:5421:07
NoticeUpdate postedTimes in UTC

Investigating

10 min 19%

Identified

40 min 81%

Updates

Times in UTC

As posted by Cartesia

Resolved2026-09-23 21:07 UTC

This incident has been resolved.

Identified2026-09-23 21:06 UTC

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

Identified2026-09-23 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 incident.

Investigating2026-09-23 20:16 UTC

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

Cartesia in the last 90 days

Full history
90 days agoToday

Incidents in 90 days

14

Days with an incident

12

Median duration

1 h 5 min

This incident

23% shorter than the median

How long each incident lasted, on the day it started. The outlined bar is this incident.

21 h 4 min
median 1 h 5 min
90 days agoToday

Other Cartesia incidents

All incidents

Cartesia·Elevated latency for instant voice cloning

This incident has been resolved.

Resolvedresolved 9 d ago

Cartesia·Managed Agents with OpenAI LLMs may see degraded performance

This incident has been resolved.

Resolvedresolved 11 d ago

Cartesia·Playground unavailable

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

Resolvedresolved 17 d ago

Cartesia·Intermittent API and Playground Errors

This incident has been resolved.

Resolvedresolved 24 d ago

Cartesia·Intermittent issues with voice cloning in APAC

This incident has been resolved.

Resolvedresolved 58 d ago

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

FAQ

Go from tracking outages to fixing production issues with Polylane.

Try Polylane