Issues with downstream LLM provider in Voice Agent API
Feb 17, 16:15 UTCFeb 17, 20:16 UTC
Duration
4h 1m
Impact
Informational
Root cause
Not disclosed
Deepgram, 90 days
19 incidents
Affected
Voice Agent APIDeepgram Public API (api.deepgram.com) - Voice Agent API
Final update
As of 10:00 UTC, the issues from OpenAI models is being resolved.
Timeline
- Resolved · Feb 17, 20:16 UTC
As of 10:00 UTC, the issues from OpenAI models is being resolved.
- Investigating · Feb 17, 16:15 UTC
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, including at least one non-OpenAI think provider. The incident started at 14:40 UTC.
More from Deepgram
Full historyElevated errors for Flux streaming STT and Voice Agent sessionslasted 6h 33mElevated errors from authentication services at one datacenterlasted 55mElevated Latency and Errors for Batch STTlasted 2h 25mElevated 5xx Errorslasted 18h 59mElevated 503 errors for bath Flux TTS requestslasted 1h 31mElevated 503 errors for Aura-2 TTSlasted 11m