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)
- 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
- update · Nov 18, 1:43 PM EST
We are seeing improvement for Cartesia voices. Deepgram and ElevenLabs issues are still ongoing.
- update · Nov 18, 2:28 PM EST
Deepgram updated status that a fix has been implemented and is monitoring results.
- 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.
- 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.
- 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.