Deepgram Transcriber Degraded

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 29m it lasted.

  Anything that failed between 2025-12-10 19:49 UTC and 2025-12-10 20:18 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. updateDec 10, 2025, 7:49 PM UTC

   We're noticing some calls failing with issues with the deepgram transcriber, we're actively monitoring it. In the meantime, we recommend switching to a different transcriber and setting up Transcriber Fallbacks to prevent calls from failing.

   provider

2. resolvedDec 10, 2025, 8:18 PM UTC

   Deepgram has resolved the issue, and we're seeing calls go through fine. We will be closely monitoring the issue. We highly recommend setting up transcriber fallbacks to avoid call failures in situations like this. https://docs.vapi.ai/api-reference/assistants/create#request.body.transcriber.DeepgramTranscriber.fallbackPlan

   provider

Corrections

None so far.

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