ElevenLabs Outage History
Recent incidents ElevenLabs has published, newest first, with how long each one lasted.
Showing 22 published incidents back to 27 May 2026.
- Minor10 Sep 202611h
EU Residency - Conversation history not showing for recent calls
- Minor9 Sep 20261d 2h
Claude MCP connection not working
- Informational7 Sep 20264h 3m
ElevenReader Elevated Error Rates
- Minor4 Sep 20267h 6m
Increase in latency in the Global Residency for Speech-to-Text and Dubbing requests
- Minor4 Sep 202631 min
EU - STT - Increase in latency in the EU Residency for Speech-to-Text requests
- Informational31 Aug 20264h 25m
Customer support ticketing system not receiving new tickets and ticket replies
- Minor27 Aug 20263 min
Batch calling degraded in EU residency
- Minor26 Aug 20265h 58m
Elevated latency on Text-to-Speech and Speech-to-Text Requests
- Minor24 Aug 20269h 53m
Media not loading across several products
- Minor18 Aug 20264 min
Inbound Twilio calls experiencing intermittent connection failures
- Minor3 Aug 20262 min
Elevated error rates on TTS, STT APIs
- Major31 Jul 20262h 20m
SIP call failures
- Minor17 Jul 202645 min
Conversation History Not Showing Recent Calls (EU Residency) - All Conversation are appearing with a delay
- Major14 Jul 20264h 21m
Speech Engine Conversation Failures
- Major9 Jul 20265h 1m
WhatsApp outbound message failures
- Minor7 Jul 20261h 34m
Image and Video Generation Errors
- Major25 Jun 20262h 10m
Agent Tool Creation and Update Does not Save
- Minor17 Jun 202619 min
Issues with logging in to the website for certain users
- Minor17 Jun 20266h 28m
UI dubbing failures
- Minor10 Jun 20261h 54m
TTV - Elevated 500 error rates
- Minor2 Jun 20267h 24m
Transient STT/STS Errors
- Minor27 May 202620 min
Failures in Exports of Studio and Dubbing projects
What this record shows
ElevenLabs runs several products behind one account — speech synthesis, voice cloning, dubbing, the audio library and the API — and they fail independently. An incident affecting dubbing will have left synthesis alone, so read the titles rather than assuming the whole platform stopped.
What this list cannot show you is quota. Character allowances are the cause most often mistaken for an outage, and exhausting one produces an error that reads like a server fault while nothing is actually broken.
ElevenLabs does not publish an uptime figure of its own, so the percentage on the main status page is calculated from this incident record.
How to read the durations
Each entry runs from when Voice AI opened the incident to when it was marked resolved. That is a generous measure: an incident is usually opened once the problem is confirmed and closed after it has been stable for a while, so the window is wider than the period in which most people were actually affected.
Severity comes from the provider. Only major and critical entries count against the uptime figure on the ElevenLabs status page, because a minor incident normally means degraded performance for some users rather than the service being unavailable.
This list is limited to what the provider has published and still exposes. Providers cap how far their public feed reaches, so an empty stretch further back means the record has aged out, not that nothing happened.
🔗 Keep checking