Outage recap · Deepgram

Deepgram outage — June 17, 2026

On June 17, 2026, Deepgram had 2 reported incidents on Deepgram's official status page. Below is what was reported — impact, timing, and the AI services the same upstream outage could affect.

400 errors with PreRecorded STT ("REMOTE_CONTENT_ERROR" / "failed to return valid data") when passing a URL

minor
Started
Jun 17, 9:35 AM EDT
Resolved
Jun 17, 3:47 PM EDT
Duration
6h 13m

Deepgram's updates (2)

  1. identified · Jun 17, 9:35 AM EDT

    Between the hours of 13:35 UTC - 19:47 UTC we noticed an increase in 400 errors returned on PreRecorded STT requests where the payload was a URL. They were transient errors, retrying the request was the recommended course of action and would typically result in a successful transcription.

  2. resolved · Jun 17, 3:47 PM EDT

    The issue was resolved at 19:47 UTC.

Updates are Deepgram's own words from its status page (status: resolved); we never add an inferred cause. The vendor's incident page ↗

Elevated errors when using Google Gemini models with Voice Agent

minor
Started
Jun 17, 2:00 PM EDT
Resolved
Jun 18, 12:00 AM EDT
Duration
10h

Deepgram's updates (4)

  1. investigating · Jun 17, 2:00 PM EDT

    We are currently investigating elevated error rates affecting Voice Agent requests that use Google Gemini models. During this period, some requests to Google models (including gemini-2.5-flash-lite) may fail or time out. Other Voice Agent functionality and non-Google models are not affected. Our team is actively working to identify the cause and restore full service. We will provide an update shortly. 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. identified · Jun 17, 4:54 PM EDT

    We have identified the cause of elevated error rates affecting Voice Agent requests that use Google Gemini models. A recent change on Google's side to how API keys operate is causing requests to fail, and our team is rolling out updated credentials to resolve it. Until the update is complete, customers may see intermittent failures for Gemini-model requests — concentrated in the first half of each hour, with most requests succeeding in the second half. Other Voice Agent models are unaffected. We are actively working on the fix and will update when resolved.

  3. identified · Jun 17, 4:55 PM EDT

    Continuing to monitor; root cause confirmed as the Google API key change.

  4. resolved · Jun 18, 12:00 AM EDT

    This incident has been resolved.

Updates are Deepgram's own words from its status page (status: resolved); we never add an inferred cause. The vendor's incident page ↗

AIDownCheck is not affiliated with Deepgram. This recap summarizes incidents published on Deepgram's official status page.