Identified - We are currently observing elevated error rates from our downstream third-party provider, Google Gemini LLMs. Deepgram infrastructure, including our canaries, remains healthy; however, Voice Agent customers using bring-your-own (BYO) Gemini LLMs may experience degraded performance or intermittent failures on LLM think requests.

We are monitoring the situation and tracking the provider’s status at https://aistudio.google.com/status. We will provide further updates as more information becomes available or if we observe broader impact.

Apr 21, 2026 - 15:59 UTC
Deepgram Public API (api.deepgram.com) Degraded Performance
Batch API Operational
Streaming API Operational
TTS API Operational
Voice Agent API Operational
Voice Agent API: Downstream Providers Degraded Performance
DG Whisper Cloud Operational
On-Premise Operational
License Validation Operational
Usage API Operational
Developer Console / Management APIs Operational
Developer Console Operational
API Playground Operational
Management APIs Operational
Documentation Operational
Developer Documentation Operational
Deepgram Website Operational
Operational
Degraded Performance
Partial Outage
Major Outage
Maintenance
Apr 23, 2026

No incidents reported today.

Apr 22, 2026

No incidents reported.

Apr 21, 2026

Unresolved incident: Voice Agent third-party provider instability (Google Gemini LLMs).

Apr 20, 2026

No incidents reported.

Apr 19, 2026

No incidents reported.

Apr 18, 2026
Resolved - This incident has been resolved.
Apr 18, 03:48 UTC
Update - We are continuing to investigate this issue.
Apr 18, 03:48 UTC
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.
Apr 17, 20:56 UTC
Apr 17, 2026
Apr 16, 2026

No incidents reported.

Apr 15, 2026

No incidents reported.

Apr 14, 2026

No incidents reported.

Apr 13, 2026
Resolved - This incident has been resolved.
Apr 13, 19:47 UTC
Monitoring - A network infrastructure fix was implemented at 18:15 UTC and the behavior was immediately resolved. We are continuing to monitor carefully.
Apr 10, 18:15 UTC
Identified - A networking incident was identified which resulted in failed callbacks on STT PreRecorded API requests and TTS Batch requests. The issue also affected Voice Agent API sessions with LLM and TTS providers. We have identified a fix and are monitoring traffic. The source of the issue is being investigated.
Apr 10, 17:27 UTC
Apr 12, 2026

No incidents reported.

Apr 11, 2026

No incidents reported.

Apr 10, 2026
Apr 9, 2026

No incidents reported.