Cartesia incident

Degraded API Performance in US Regions

Resolved after 5 hours 54 minutes, affecting Voice Cloning, on October 7, 2026.

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.

Started
Oct 07, 2026, 04:29 PM UTC
Resolved
Oct 07, 2026, 10:23 PM UTC
Duration
5h 54m
Detected by Pingoru
Oct 07, 2026, 04:29 PM UTC

Affected components

Voice Cloning

Update timeline

  1. investigating Oct 07, 2026, 04:29 PM UTC

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

  2. monitoring Oct 07, 2026, 04:50 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.

  3. investigating Oct 07, 2026, 09:13 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, 09:16 PM UTC

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

  5. resolved Oct 07, 2026, 10:23 PM UTC

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

  6. resolved Oct 07, 2026, 10:23 PM UTC

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

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

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

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

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

  9. 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.

  10. 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.

  11. 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.

Your product runs on more than Cartesia

Add the vendors you depend on and get one message when any of them reports trouble. Free for 3 vendors, no card.

Add your stack →