Deepgram outage history

Every smaller Deepgram incident

Minor and short incidents from the Deepgram status page, newest first, each with a line from the official updates. Times are UTC.

October 2026

• Oct 14, 2026, 19:29 UTC · Elevated 503 errors for bath Flux TTS requests

  1 hour 31 min · rated "Minor"

  "This issue has been resolved."

• Oct 13, 2026, 17:58 UTC · Elevated 503 errors for Aura-2 TTS

  11 minutes · rated "Minor"

  "This issue has been resolved."

• Oct 8, 2026, 02:58 UTC · Elevated error rates for Flux TTS

  1 hour 27 min · rated "Minor"

  "We experienced 2 bursts of elevated error rates between 02:58 - 03:16 UTC and 03:53 - 04:18 UTC. The issue is now resolved."

• Oct 5, 2026, 09:55 UTC · Elevated errors for Flux TTS

  2 hours · rated "Minor"

  "We are investigating elevated error rates for some Flux Text-to-Speech streaming requests in the US, beginning around 09:55 UTC. Affected users may see connections close unexpectedly with a 1011 / NET-0000 error."

• Oct 3, 2026, 15:52 UTC · Elevated errors for Flux TTS

  2 hours 1 min · rated "Minor"

  "The issue has been identified and a fix is being implemented."

September 2026

• Sep 30, 2026, 19:29 UTC · Elevated API errors

  10 minutes · rated "Minor"

  "Between 19:29 and 19:39 UTC, some API requests failed with HTTP 500 errors or timed out. This happened in two short bursts of about 1-2 minutes each, during a planned update to our authentication service."

• Sep 28, 2026, 17:53 UTC · Elevated Latency and Errors for Batch STT (US)

  duration not stated · rated "Minor"

  "An issue affecting some of our pre-recorded transcription servers slowed request processing. As requests took longer to complete, some customers saw elevated latency or received 429 errors."

• Sep 28, 2026, 17:04 UTC · Elevated latency on Flux STT (US)

  4 minutes · rated "Minor"

  "We are investigating an issue with Flux STT that may result in some US connections to see delayed transcripts and some disconnects."

• Sep 25, 2026, 09:45 UTC · Elevated Flux TTS 1011 Error Rate

  3 hours 60 min · rated "Minor"

  "This issue has been resolved."

• Sep 22, 2026, 12:10 UTC · Aura-2 TTS Elevated Error Rates for English Voices

  40 minutes · rated "Major"

  "We are investigating elevated 503 Service Unavailable errors affecting some Aura-2 TTS requests for English voices. We are working to identify the cause and restore full service availability."

• Sep 2, 2026, 20:22 UTC · ISP Backbone Degradation

  3 hours 6 min · rated "Minor"

  "The upstream ISP failure has been mitigated by rerouting all traffic around that provider."

August 2026

• Aug 25, 2026, 18:01 UTC · [Deepgram EU API] Flux-Multi STT Outage

  duration not stated · marked as no impact

  "Resolved Between 07:13 and 09:00 UTC, flux-general-multi Speech-to-Text requests on api.eu.deepgram."

• Aug 25, 2026, 16:41 UTC · [Deepgram API] Elevated Streaming STT Error Rates

  duration not stated · marked as no impact

  "Between 23:18 and 23:45 UTC, a portion of streaming STT connection requests failed with 5XX errors and timeouts. While rolling out a new data center, we detected streaming errors and immediately removed it from rotation."

• Aug 20, 2026, 15:52 UTC · Elevated 5XX Error Rate for v1/auth/grant

  1 hour 9 min · rated "Minor"

  "We're seeing elevated error rate for authentication services. We are currently investigating the issue"

• Aug 13, 2026, 13:17 UTC · Elevated 5XX Error Rate for v1/auth/grant

  12 minutes · rated "Minor"

  "We've resolved the issue and the service is back to normal."

• Aug 4, 2026, 14:30 UTC · [Deepgram API] Elevated Batch and Streaming STT Error Rates

  3 hours 40 min · rated "Minor"

  "We are currently investigating an issue where batch and streaming STT requests have degraded performance."

July 2026

• Jul 28, 2026, 14:00 UTC · [Deepgram API] Elevated Batch Error Rates: 400 error code responses

  23 hours 8 min · rated "Minor"

  "We are currently investigating an issue where some batch requests are returning 400 errors due to remote content download errors. Retrying the request one or more times often succeeds."

• Jul 24, 2026, 13:18 UTC · Intermittent Connectivity Issues Due to AWS US-WEST-2 Infrastructure Event

  4 minutes · marked as no impact

  "Between approximately 10:55 and 12:00 UTC on July 24, an upstream infrastructure issue in AWS's US-WEST-2 region caused intermittent connectivity problems that may have affected Deepgram services and customer infrastructure - including..."

• Jul 21, 2026, 13:45 UTC · Voice Agent API: Google/Gemini LLM errors

  1 hour 34 min · rated "Minor"

  "Starting at 13:45 PM UTC, some Voice Agent sessions using Google/Gemini without a pinned model version received failed responses due to a routing issue introduced in this morning's deploy."

• Jul 7, 2026, 15:56 UTC · Elevated 5XX Errors for Flux STT Requests

  2 hours 23 min · marked as no impact

  "Flux STT experienced elevated WebSocket streaming errors between 15:56 UTC and 18:20 UTC."

June 2026

• Jun 24, 2026, 14:15 UTC · ISP Network-Related Issue

  duration not stated · marked as no impact

  "An upstream ISP issue may have caused intermittent WebSocket connection failures, handshake timeouts, and degraded streaming connectivity. Incident time: 01:10 - 01:52 UTC"

• Jun 23, 2026, 15:06 UTC · Voice Agent third-party provider Instability (Anthropic LLMs)

  2 hours 16 min · rated "Minor"

  "Anthropic has resolved this incident. Incident end time: Jun 23, 2026, 16:44 UTC"

• Jun 18, 2026, 21:42 UTC · Degraded performance on Nova streaming STT

  duration not stated · marked as no impact

  "Nova-3 and Nova-2 streaming STT experienced elevated websocket connection errors and websocket disconnections between 13:00 - 16:00 UTC."

• Jun 17, 2026, 18:00 UTC · Elevated errors when using Google Gemini models with Voice Agent

  10 hours · rated "Minor"

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

• Jun 17, 2026, 13:35 UTC · 400 errors with PreRecorded STT ("REMOTE_CONTENT_ERROR" / "failed to return valid data") when passing a URL

  6 hours 13 min · rated "Minor"

  "The issue was resolved at 19:47 UTC."

• Jun 15, 2026, 11:00 UTC · Degraded performance - Flux streaming Speech-to-Text

  26 hours 60 min · rated "Minor"

  "This incident has been resolved. A degradation affecting a subset of streaming Speech-to-Text (Flux) sessions, where connections terminated before returning a transcript, has been mitigated and service has been operating normally since."

May 2026

• May 22, 2026, 21:00 UTC · Outbound networking issues affecting STT, TTS streaming and batch service

  duration not stated · marked as no impact

  "Some API requests may have experienced elevated error rates for approximately 2-3 minutes starting at 16:43 UTC on May 22, 2026. The issue has been resolved now."

• May 18, 2026, 23:36 UTC · Voice Agent - Elevated 4xx Error Rates

  duration not stated · rated "Minor"

  "Between 22:06 and 22:12 UTC, a subset of Voice Agent requests returned elevated 4xx errors following a recent deploy. The deploy has been rolled back and the service is operating normally."

• May 14, 2026, 18:52 UTC · Elevated 5XX Errors for Non-English Batch STT Requests with Redaction

  9 minutes · rated "Minor"

  "This issue has been resolved."

• May 12, 2026, 16:18 UTC · Intermittent 404 HTTP errors Batch STT English

  1 hour 49 min · rated "Minor"

  "During the affected time period, some English batch speech-to-text requests intermittently returned 404 Not Found HTTP errors."

• May 11, 2026, 16:35 UTC · Voice Agent third-party provider instability (ChatGPT 4o)

  24 hours 20 min · rated "Minor"

  "We are currently observing elevated error rates from our downstream third-party provider, OpenAI specifically with the ChatGPT 4o model. Deepgram infrastructure, including our canaries, remains healthy."

April 2026

• Apr 27, 2026, 14:14 UTC · Outbound networking issues affecting STT fetch requests and callbacks, Dashboard API requests, and Voice Agent 3rd party providers

  duration not stated · marked as no impact

  "A small number of customers experienced disruptions to STT fetch requests, callbacks, and third-party providers within Voice Agent, as well as 503 errors on API calls for usage lookups and token creation."

• Apr 24, 2026, 05:45 UTC · Voice Agent third-party provider instability (Claude Sonnet 4.5)

  7 days 13 hours · rated "Minor"

  "We are currently observing elevated error rates from our downstream third-party provider, Anthropic specifically with the Claude Sonnet 4.5 model. Deepgram infrastructure, including our canaries, remains healthy."

• Apr 21, 2026, 15:59 UTC · Voice Agent third-party provider instability (Google Gemini LLMs)

  10 days 2 hours · rated "Minor"

  "We are currently observing elevated error rates from our downstream third-party provider, Google Gemini LLMs."

• Apr 17, 2026, 20:56 UTC · Issues with downstream LLM provider in Voice Agent API

  6 hours 52 min · marked as no impact

  "We are currently seeing elevated error rates from OpenAI models. To avoid downtime, please define multiple LLM providers (https://developers.deepgram."

• Apr 10, 2026, 17:27 UTC · Outbound networking issues affecting STT PreRecorded API requests with callbacks, TTS Batch (HTTP) requests with callbacks, and Voice Agent API BYO 3rd party providers (LLM and TTS)

  3 days 2 hours · marked as no impact

  "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."

March 2026

• Mar 25, 2026, 15:16 UTC · Degraded API Performance

  duration not stated · marked as no impact

  "Between 15:16 and 15:32 UTC on March 25, 2026, we noticed an increased rate of API requests returning errors, including 403, 404, and 504 status codes. The issue has been identified and resolved."

• Mar 20, 2026, 16:53 UTC · Voice Agent API Degraded Service

  3 days 2 hours · rated "Minor"

  "There is an ongoing OpenAI outage that is affecting our Voice Agent. To avoid downtime, please define multiple LLM providers (https://developers.deepgram."

• Mar 18, 2026, 15:00 UTC · Voice Agent API Degraded Performance

  1 hour 60 min · rated "Minor"

  "We are continuing to monitor this issue."

• Mar 5, 2026, 00:59 UTC · Issues with downstream LLM provider in Voice Agent API

  26 minutes · rated "Minor"

  "There is an ongoing OpenAI outage that is affecting our Voice Agent. To avoid downtime, please define multiple LLM providers (https://developers.deepgram."

February 2026

• Feb 26, 2026, 17:16 UTC · [Deepgram API] Elevated Errors for Streaming STT

  8 hours 50 min · marked as no impact

  "We are currently investigating an issue that results in increased Speech-to-Text result latency."

• Feb 24, 2026, 02:00 UTC · [Deepgram API] Flux SDK Session Disruptions

  duration not stated · marked as no impact

  "A temporary issue during a Flux-related update caused intermittent SDK session errors. The issue was identified and resolved. 2:00 AM UTC - 13:45 UTC"

• Feb 23, 2026, 17:58 UTC · Issues with downstream LLM provider in Voice Agent API

  20 hours 30 min · marked as no impact

  "The upstream Anthropic incident affecting Claude models has been resolved and error rates have returned to normal. Voice Agent functionality should now be operating as expected."

• Feb 17, 2026, 16:15 UTC · Issues with downstream LLM provider in Voice Agent API

  4 hours 1 min · marked as no impact

  "As of 10:00 UTC, the issues from OpenAI models is being resolved."

• Feb 16, 2026, 17:08 UTC · Issues with downstream LLM provider in Voice Agent API

  6 hours 24 min · marked as no impact

  "We are currently seeing elevated error rates from OpenAI models. To avoid downtime, please define multiple LLM providers (https://developers.deepgram."

• Feb 12, 2026, 17:47 UTC · Issues with downstream LLM provider in Voice Agent API

  27 hours 41 min · rated "Minor"

  "The incident has been resolved."

• Feb 4, 2026, 16:52 UTC · Issues with downstream LLM provider in Voice Agent API

  1 hour 55 min · rated "Minor"

  "The downstream provider indicated the issue was resolved. There was an outage between 16:20 UTC / 8:20 PT and 16:55 UTC / 8:55 PT"

• Feb 3, 2026, 15:35 UTC · Issues with downstream LLM provider in Voice Agent API

  7 hours 60 min · rated "Minor"

  "The incident has been resolved. The downstream provider's status page indicates the issues were resolved at 9:56 PT / 17:56 UTC"

January 2026

• Jan 28, 2026, 22:10 UTC · Elevated Connection Errors

  7 days 21 hours · rated "Minor"

  "We saw elevated connection errors from 19:12 to 19:19 UTC, and 20:10 to 20:31 UTC. We're no longer seeing spikes in errors, but we're continuing to monitor the situation."

• Jan 22, 2026, 23:45 UTC · Degraded Transcripts on Nova-3 Multilingual STT Model

  duration not stated · rated "Minor"

  "From 21:38 - 23:39 UTC on 2026-01-22, requests for Deepgram's Nova-3 multilingual STT model received degraded transcripts due to a faulty model release."