Cartesia: Intermittent issues with voice cloning in APAC
AWS us-west-2 outage, Sep 3, 2026 · 20 vendors, 20 incidents
Cartesia’s incident started in the same window without naming AWS (timing only, not evidence of a link). (timing only, posted +44 min vs AWS’s own post)
Swipe sideways to see the whole diagram.
Mermaid source
flowchart LR
root["AWS us-west-2<br/>posted 21:49 UTC"]:::root
before["Posted before AWS did<br/>3 vendors, 3 blamed AWS<br/>Materialize, Temporal Cloud, Semgrep"]:::blames
root --> before
h1["Within an hour<br/>4 vendors, 4 blamed AWS<br/>Dropbox, Teleport, Wiz, SurveyMonkey"]:::blames
root --> h1
me["Cartesia (this incident)<br/>posted +44 min"]:::me
root -.->|"same window"| meFull event: timeline, evidence and all vendors →
Detected automatically from incidents that started together and named the same provider. A link means one vendor’s incident named another, not a confirmed cause.
Affected components: Voice Cloning
Timeline of updates
- investigating
We are investigating the issue.
- monitoring
We have mitigated the issue on our end and are continuing to monitor the state of our service.
- monitoring
We have mitigated the issue on our end and are continuing to monitor the state of our service.
- resolved
This incident has been resolved.
Archive proof
Rewindex commits each version of an incident it captures to a daily checkpoint, chains it to the day before, and has the checkpoint timestamped by FreeTSA and DigiCert. That proves this record existed by then and has not been changed since, by anyone, Rewindex included.
How the archive is checked, and what it cannot prove.
First version captured 17:03 UTC
In the 2026-10-19 checkpoint, timestamped by FreeTSA and DigiCert on Oct 20, 00:41 UTC. Record hash
9d8d47a01b4848c6…
Impact, status and times are the vendor’s own, as last archived. View on status.cartesia.ai (opens in new tab).