AI STATUS BOARD

ElevenLabs outage report · Wednesday 21 October 2026

ElevenLabs went
down 8 times
in one day.

ElevenLabs reported “Increased Dubbing Latency and Failure Rate”, “Agent SIP Conversation Disruption”, “EU Residency - Issue with the Agents platform, TTS and Scribe in the EU residency server”, “Website Slowness and API Request Latency”, “Website authentication rejecting all frontend requests”, “Request failures with the V3 model”, “[Isolated environments] Issue with voices on EU and India Residency environments” and “EU Agents disruption in SIP calls”. 0 min in total, all resolved.

In numbers

RESOLVED 22:10 UTC
Down in total
0 min
Outages
8
Longest
0 min
Updates from ElevenLabs
33

The day, hour by hour

UTC
00:0006:0012:0018:0024:00

What ElevenLabs said, as it happened

17:30 → 12:51 UTC · EU Agents disruption in SIP calls

0 min
  1. 17:30resolved

    The issue has been resolved. EU SIP services are operational and stable.

  2. 17:30monitoring

    Error rates have returned to normal. We're currently monitoring the situation to confirm that the issue has been resolved

  3. 17:30investigating

    We are currently still investigating. We will post updates here as soon as more information becomes available

  4. 17:30investigating

    We are still investigating. We will continue posting updates as more information becomes available

  5. 17:30investigating

    We're currently investigating disruptions in SIP calls in our EU residency.

17:30 → 07:07 UTC · [Isolated environments] Issue with voices on EU and India Residency environments

0 min
  1. 17:30resolved

    The issue with the Isolated Environments has been resolved after we released a fix. The incident was caused by a change made to how we cache Voice Library voices in data residency environments. The issue only surfaced gradually hours after we released it as the cache for these voices were getting invalidated.

  2. 17:30monitoring

    We have released a fix, and the error rate is decreasing. We are monitoring the performance.

  3. 17:30investigating

    We are investigating an issue with adding/missing voices in the EU and India Residency Environments. THe

17:30 → 11:35 UTC · Request failures with the V3 model

0 min
  1. 17:30resolved

    The issue has been completely resolved, and the requests with the v3 model are being processed.

  2. 17:30investigating

    We are currently investigating an issue causing request failures with the v3 model. This only affects the v3 model.

17:30 → 13:39 UTC · Website authentication rejecting all frontend requests

0 min
  1. 17:30resolved

    Website should work now

  2. 17:30identified

    We are experiencing a temporary issue with website authentication rejecting all authentication tokens. We are working on a fix

17:30 → 19:45 UTC · Website Slowness and API Request Latency

0 min
  1. 17:30resolved

    As of 7:45 PM UTC, all affected services have fully recovered and are operating normally. **Agents Platform** and **Audio Platform (Website)** have returned to full health. Text-to-Speech (TTS), Speech-to-Text (STT), and Dubbing APIs were unaffected throughout the incident. The root cause has been identified and remediated. We will be conducting a thorough post-incident review and will share further details in a follow-up report. We apologize for the disruption and appreciate your patience throughout this incident. If you are still experiencing any issues, please don't hesitate to contact our support team.

  2. 17:30monitoring

    Affected services continue to show sustained improvement following the changes implemented earlier. We are continuing to monitor key metrics and will confirm full resolution once we are satisfied with stability across baseline error rates. Next update in 15-20 minutes.

  3. 17:30monitoring

    We have implemented changes to the affected services that have resulted in signs of recovery and improved performance. We are closely monitoring to confirm stability and will provide an another update in 15–20 minutes.

  4. 17:30identified

    Our team remains fully engaged and continues to work through active lines of investigation. All previously noted affected and operational components remain in the same state. We will provide another update in 15-20 minutes

  5. 17:30identified

    We are continuing to investigate all possible root causes and eliminate potential causes. Additionally we are clarifying affected products below. **What's affected:** - **Agents Platform** - degraded performance due to issues around conversation initiation. Conversations that do start function as normal thus API customers should retry failed initiation conversations. - **Website** - intermittent slowness **What's working normally:** - Text-to-Speech (TTS) API - Speech-to-Text (STT) API - Dubbing API Our engineering team remains fully engaged and is continuing to work through active lines of investigation alongside our infrastructure provider. We are iterating on potential mitigations and monitoring the results closely. We will continue to provide updates every 15-20 minutes.

  6. 17:30identified

    Our team continues to actively investigate the degraded performance affecting services. We are working through several lines of investigation in parallel and methodically testing potential contributing factors. This remains escalated with our infrastructure provider and internal leadership, with additional engineering resources dedicated to this effort. While a definitive root cause has not yet been identified, each step is helping us build a clearer picture of the underlying issue. We understand the impact this is having and are treating this with the highest priority. We will provide another update in 15-20 minutes.

  7. 17:30identified

    Our engineering team is actively exploring multiple remediation paths in parallel while working to isolate the root cause. We have escalated this issue both to our infrastructure provider and to internal leadership to ensure it receives the highest level of attention and resources. A definitive root cause has not yet been identified, but we are making iterative changes and closely monitoring their impact. We will continue to provide updates as our investigation progresses.

  8. 17:30identified

    Our engineering team is continuing to investigate issues with the cloud provider components. Multiple engineering teams and leadership is involved in the efforts. We'll continue monitoring closely and provide timely updates as the situation evolves.

  9. 17:30identified

    We have isolated the components responsible for performance degradation and are attempting to implement workarounds to bypass the affected cloud provider services.

  10. 17:30identified

    We have identified an underlying issue with our cloud provider that is impacting service availability.

  11. 17:30investigating

    We are currently investigating an issue with website and API requests and are working to identify the root cause as quickly as possible. We will provide an update as soon as more information becomes available. TTS API request and Agents conversations are working. There may be issues related to API services that affect conversation initiation.

17:30 → 09:42 UTC · EU Residency - Issue with the Agents platform, TTS and Scribe in the EU residency server

0 min
  1. 17:30resolved

    The issue has been resolved. We will publish a public write-up on this status page once the investigation is completed.

  2. 17:30monitoring

    We have released an update, and the error rate is back to normal. We are currently monitoring the situation.

  3. 17:30investigating

    We are currently investigating an issue with the Agents platform, TTS and Scribe in the EU residency server.

17:30 → 15:43 UTC · Agent SIP Conversation Disruption

0 min
  1. 17:30resolved

    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.

  2. 17:30investigating

    We are currently investigating an issue causing call failures in Agent conversations using SIP. Non-SIP Agent conversations are unaffected.

17:30 → 22:10 UTC · Increased Dubbing Latency and Failure Rate

0 min
  1. 17:30resolved

    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.

  2. 17:30monitoring

    Errors have returned to baseline since 17:10 UTC. We are continuing to work with an upstream provider for full mitigation.

  3. 17:30monitoring

    Since 16:30 UTC, we have observed recurrence of Dubbing errors and latency. We're working with an upstream provider for full mitigation, and will continue to post updates as new information arises.

  4. 17:30monitoring

    We have traced error metrics as they have returned to baseline. We're currently monitoring to ensure full resolution.

  5. 17:30investigating

    We are currently investigating increased latency and request failures affecting Dubbing.

Quoted from ElevenLabs's status page. Times in UTC.

Was it just ElevenLabs?

Yes. No other company on the board reported a problem during these outages.

Smaller problems that day:

  • Lovable00:56 → 02:47Lovable backends stuck after restart
  • Cursor10:37 → 10:21Investigating service degradation
  • Cursor15:46 → 17:40Investigating service degradation
  • Lovable16:33 → 18:42Delays syncing with GitHub
  • Cursor17:40 → 17:53Elevated errors for Bitbucket Cloud integrations
  • Lovable17:57 → 18:20Lovable is slow at answering

ElevenLabs's record

Incidents, last 90 days
21
Typical length
0 min

About as long as a typical ElevenLabs incident.

All ElevenLabs outages

Hear first next time

A notification the moment ElevenLabs breaks, and when it's back.

Questions about this outage

Why was ElevenLabs down on 21 October 2026?

ElevenLabs described it as “Increased Dubbing Latency and Failure Rate” and “Agent SIP Conversation Disruption” and “EU Residency - Issue with the Agents platform, TTS and Scribe in the EU residency server” and “Website Slowness and API Request Latency” and “Website authentication rejecting all frontend requests” and “Request failures with the V3 model” and “[Isolated environments] Issue with voices on EU and India Residency environments” and “EU Agents disruption in SIP calls”. Its updates are quoted on this page; if it posts a cause later, it shows up there.

How long was ElevenLabs down?

0 min in total, across 8 outages: 0 min from 17:30 UTC, 0 min from 17:30 UTC, 0 min from 17:30 UTC, 0 min from 17:30 UTC, 0 min from 17:30 UTC, 0 min from 17:30 UTC, 0 min from 17:30 UTC, 0 min from 17:30 UTC.

Were other AI tools down at the same time?

No. No other company on our board reported a problem during these outages.

How do I know next time ElevenLabs goes down?

Turn on alerts on AI Status Board. You get a notification the moment ElevenLabs breaks and again when it is back.