# ElevenLabs: Multiple US endpoints experiencing timeouts and latency

- Impact (vendor’s label): major
- Status: resolved
- Started: 2026-10-13 09:21 UTC · Resolved: 2026-10-13 14:18 UTC · Duration: 5.0 h
- Updates: 8 · Affected components: RAG, RAG, Other API endpoints, Other API endpoints, Telephony, Telephony, UI, UI, Quality, Quality, Conversations, Conversations, Integrations, Integrations
- [Vendor status page: https://status.elevenlabs.io/incidents/01M4T91CTNSTQ93Q2Q31VQDBWH](https://status.elevenlabs.io/incidents/01M4T91CTNSTQ93Q2Q31VQDBWH)
- [Company: ElevenLabs](https://rewindex.com/company/elevenlabs.md)

## Summary

Multiple ElevenLabs US endpoints, including some Elevenagents endpoints, experienced elevated latency, timeouts and failed requests in a major incident starting 2026-10-13 09:21 UTC. It lasted 4 h 57 min, resolving at 2026-10-13 14:18 UTC after work with its data service provider; stable service was confirmed, with root cause analysis still pending. _(machine-written, sol)_
## Timeline of updates

- **investigating** 2026-10-13 09:21 UTC: We are investigating elevated latency and timeouts affecting multiple endpoints, including some Elevenagents endpoints. Some requests may be slow or fail. Our team is actively looking into the cause.
- **resolved** 2026-10-13 09:47 UTC: Error rates have returned to normal. We are currently still investigating the cause of this downtime and will update the status page with an RCA as soon as possible.
- **identified** 2026-10-13 09:57 UTC: We’re seeing error rates rise again, so calls may still fail or experience increased latency.
- **monitoring** 2026-10-13 10:38 UTC: Error rates are still flaky. We are monitoring the affected endpoints to confirm stability and are working with our data provider on a root cause analysis.
- **identified** 2026-10-13 11:42 UTC: We are still seeing elevated errors and timeouts on the affected endpoints, and requests may continue to fail. We are actively working with our data provider to restore full service and bring the endpoints back online.
- **identified** 2026-10-13 12:54 UTC: We are actively working with our data service provider to ensure endpoint stability. We will update the status page as soon as we have received confirmation that all our endpoints are back to normal.
- **monitoring** 2026-10-13 13:42 UTC: Error rates have continued to stabilize. We are continuing to monitor the affected endpoints to ensure service remains steady.
- **resolved** 2026-10-13 14:18 UTC: The incident is resolved. Error rates are back to normal, and stable service has been confirmed. We will publish a Root cause analysis once our review of the incident is complete.

## Rewindex changes for this incident

- 2026-10-13 09:21 UTC: [Major incident: Multiple US endpoints experiencing timeouts and latency](https://rewindex.com/change/i3b89d1e45de51f.md)


---
Canonical: https://rewindex.com/company/elevenlabs/incidents/01M4T91CTNSTQ93Q2Q31VQDBWH · Markdown: https://rewindex.com/company/elevenlabs/incidents/01M4T91CTNSTQ93Q2Q31VQDBWH.md · JSON: https://rewindex.com/api/v1/companies/elevenlabs/incidents/01M4T91CTNSTQ93Q2Q31VQDBWH · Generated 2026-10-18T09:58:55.010Z