Increase in latency in the Global Residency for Speech-to-Text and Dubbing requests

What to do

• Check whether your product depends on ElevenLabs. Check your stack

  Paste a package.json, lockfile, Terraform or a list of domains at down.guide/stack to see every provider you depend on.

• Confirm your retries, queues and scheduled jobs caught up after the 7h 6m it lasted.

  Anything that failed between 2026-09-04 13:55 UTC and 2026-09-04 21:01 UTC may need a replay.

• Subscribe to ElevenLabs's feed to hear about the next one first. RSS feed

  https://down.guide/feed?provider=elevenlabs works in Slack (/feed subscribe), Discord feed bots and any RSS reader.

Updates from ElevenLabs 4

1. investigatingSep 4, 2026, 1:55 PM UTC

   We're investigating a latency increase on the Global Residency server for Speech-to-Text and Dubbing models, affecting a small subset of requests.

   provider

2. identifiedSep 4, 2026, 2:16 PM UTC

   We've identified the root cause and are rolling out a fix. Error rates should be improving, and we're continuing to monitor.

   provider

3. monitoringSep 4, 2026, 2:34 PM UTC

   The issue has been fixed, the error rate should be zero. We are currently monitoring the situation.

   provider

4. resolvedSep 4, 2026, 9:01 PM UTC

   After completing the monitoring stage, we have confirmed that STT latency has returned to baseline stability.

   provider

Corrections

None so far.

Something wrong on this page? Report an error or send us a note. Every fix is listed here.