Deepgram incident

Issues with downstream LLM provider in Voice Agent API

Informational Resolved Upstream link ↗

Started

April 17, 2026 at 08:56 PM UTC

Duration

6h 52m

Resolved

April 18, 2026 at 03:48 AM UTC

Updates timeline

  1. Investigating

    We are currently seeing elevated error rates from OpenAI models. To avoid downtime, please define multiple LLM providers (https://developers.deepgram.com/docs/voice-agent-llm-models#using-multiple-llm-providers) in your Voice Agent configuration.

  2. Investigating

    We are continuing to investigate this issue.

  3. Resolved

    This incident has been resolved.

Live Deepgram status

Current indicator + 24h latency

All incidents

Cross-service timeline

Subscribe via RSS

Atom feed for any reader