After further monitoring, we can confirm that the root cause of the conversation initiation failures has been resolved. We will post a root cause analysis for the incident after further review.
This incident has been resolved. For a full timeline and Root Cause Analysis, see the US incident: https://status.elevenlabs.io/united-states/incidents/01M7QMQH05JXV3SKSM1H6PJZD2
Between 09:15 and 11:15 UTC on Nov 4, some Agent conversations in the EU using Eleven v4 Turbo had choppy audio, with parts of the agent's speech missing. This was caused by Eleven v4 Turbo generating audio slower than real time under high load. We have rolled out a fix that increases v4 Turbo throughput, and we are adding alerting to detect this earlier.
We have not seen any further errors after the fix was applied.
Users are now able to sign-in successfully again.
Between 03:25 and 04:44 UTC on October 13, 2026, some requests to create an Instant Voice Clone failed with an error. This affected the Voice Lab in the app and the Voices API endpoint (POST /v1/voices/add), when background noise removal was turned on. Clones created without background noise removal weren’t affected.
We experienced a transient error due to a heavy traffic spike. We will implementing improvements to be more resilient in the future.
After several hours of monitoring, our metrics show that error rate has remained at its stable baseline since 17:55 UTC; the increase in Dubbing platform latency and failure rate is now resolved.
We have monitored error metrics and have confirmed that as of 15:15 UTC, we do not see continuing Agent SIP conversation failures. We will conduct an internal investigation and post a full Root Cause Analysis upon conclusion.
Music had reduced availability after a latent infrastructure configuration issue was triggered by routine automated maintenance. This stopped new instances from starting and prevented automated recovery, and service was restored by manual intervention.
The service is now fully operational again.
Our engineers have confirmed that STT latency has fully recovered.
We can confirm that the issue has been fixed and that the service is fully operational.
Resolution time was 14:18 UTC
We will post the RCA to the status page after the investigation.
Our engineers have confirmed full recovery of the Conversation Search functionality in the web UI and the API.
Our engineers have deployed a fix that has fully restored Claude MCP functionality.
After completing the monitoring stage, we have confirmed that STT latency has returned to baseline stability.
The issue has been resolved, everything is back at normal.