V
Outage recap · Vapi

Vapi outage — November 18, 2026

On November 18, 2026, Vapi had 2 reported incidents on Vapi's official status page. Below is what was reported — impact, timing, and the AI services the same upstream outage could affect.

Model provider failures ongoing across Cartesia, Deepgram and Elevenlabs

resolved
Started
Nov 18, 1:01 PM EST
Resolved
Nov 18, 4:20 PM EST
Duration
3h 20m

Vapi's updates (6)

  1. update · Nov 18, 1:01 PM EST

    See status pages for Cartesia, Deepgram and Elevenlabs for updates. https://status.elevenlabs.io/united-states/incidents/01M7QMQH05JXV3SKSM1H6PJZD2 https://status.deepgram.com/ For get out of trouble alternatives: - for Voices, consider xAI (Vapi V2) or Minimax - for English - consider AssemblyAI or Sonion; for multi-lingual Soniox

  2. update · Nov 18, 1:43 PM EST

    We are seeing improvement for Cartesia voices. Deepgram and ElevenLabs issues are still ongoing.

  3. update · Nov 18, 2:28 PM EST

    Deepgram updated status that a fix has been implemented and is monitoring results.

  4. update · Nov 18, 3:45 PM EST

    ElevenLabs latency is back to normal levels and we’re seeing a reduction in error rates. ElevenLabs is currently still monitoring to confirm resolution.

  5. update · Nov 18, 4:04 PM EST

    Per ElevenLabs, systems are now operational across all products. We are still monitoring Deepgram status for full recovery.

  6. resolved · Nov 18, 4:20 PM EST

    Model issues appear to be resolved according to each provider and latency monitoring internally.

What our checks recorded

We checked Vapi 40 times from Vapi's start time to its resolution, once every five minutes. Every one of them reached Vapi's site, so this incident did not show up as a failed page load. Our check loads the public site; it cannot see an API error or a broken feature. Median response time was 152 ms, against 177 ms over the 24 hours before. Vapi posted the incident at Nov 18, 1:01 PM EST.

Updates are Vapi's own words from its status page (status: resolved); we never add an inferred cause.

Deepgram STT service degraded

resolved
Started
Nov 18, 5:22 PM EST
Resolved
Nov 18, 7:12 PM EST
Duration
1h 50m

Vapi's updates (4)

  1. update · Nov 18, 5:22 PM EST

    Customers are still seeing degraded service with Deepgram Flux models. We have escalated to Deepgram and are investigating the issue.

  2. update · Nov 18, 5:47 PM EST

    We have identified the root cause and are implementing a fix.

  3. update · Nov 18, 6:32 PM EST

    Errors on Flux models are reducing and we are monitoring improvement.

  4. resolved · Nov 18, 7:12 PM EST

    We are seeing latency and call completion return to normal. We will continue to monitor for additional issues.

What our checks recorded

We checked Vapi 22 times from Vapi's start time to its resolution, once every five minutes. Every one of them reached Vapi's site, so this incident did not show up as a failed page load. Our check loads the public site; it cannot see an API error or a broken feature. Median response time was 186 ms, against 176 ms over the 24 hours before. Vapi posted the incident at Nov 18, 5:22 PM EST.

Updates are Vapi's own words from its status page (status: resolved); we never add an inferred cause.

AIDownCheck is not affiliated with Vapi. This recap summarizes incidents published on Vapi's official status page.