Elevated Error Rates with Deepgram Transcriber

What to do

• Check whether your product depends on Vapi. 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 3h 20m it lasted.

  Anything that failed between 2026-02-11 17:10 UTC and 2026-02-11 20:30 UTC may need a replay.

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

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

Updates from Vapi 2

1. updateFeb 11, 2026, 5:10 PM UTC

   We are currently observing elevated error rates affecting calls that use the Deepgram transcriber. Impacted calls may terminate unexpectedly with the ended reason call.in-progress.error-vapifault-deepgram-transcriber-failed. While we work to resolve this, we recommend switching to an alternative transcriber or configuring a transcriber fallback plan to ensure call continuity. You can set up fallbacks by following the guide here: https://docs.vapi.ai/customization/transcriber-fallback-plan We are actively monitoring the situation and will provide updates as more information becomes available.

   provider

2. resolvedFeb 11, 2026, 8:30 PM UTC

   Deepgram had an issue while upgrading their system, which caused 429 errors. They've fixed it and are implementing controls to prevent recurrence.

   provider

Corrections

None so far.

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