Deepgram Outage History

57 incidents recorded over the last 365 days, 57 of them resolved. Durations are measured from when PulsAPI first saw the problem to when it cleared, which is usually longer than the vendor's own figure.

Live Deepgram status100.00% uptime history

Every Recorded Deepgram Incident

Deepgram incidents, newest first, with date, duration and status.
DateIncidentDurationStatus
Oct 8, 2026Elevated error rates for Flux TTSWe experienced 2 bursts of elevated error rates between 02:58 - 03:16 UTC and 03:53 - 04:18 UTC. The issue is now resolved.1h 27mResolved
Oct 5, 2026Elevated errors for Flux TTSThis incident has been resolved.22 minResolved
Oct 3, 2026Elevated errors for Flux TTSThis incident has been resolved.2h 0mResolved
Sep 30, 2026Elevated API errorsBetween 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. Services have…9 minResolved
Sep 28, 2026Elevated Latency and Errors for Batch STT (US)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. We identified and mitigated…-231 minResolved
Sep 28, 2026Elevated latency on Flux streaming (US)Elevated latency on Flux STT (US regions). Between 17:04 and 17:07 UTC, a small share of Flux STT connections in some US regions saw delayed transcripts and some disconnects. This issue has been resolved and service has…-91 minResolved
Sep 28, 2026Elevated latency on Flux STT (US)This incident has been resolved.3 minResolved
Sep 25, 2026Elevated Flux TTS 1011 Error RateThis issue has been resolved.3h 59mResolved
Sep 22, 2026Aura-2 TTS Elevated Error Rates for English VoicesThe issue has been resolved.-112 minResolved
Sep 2, 2026ISP Backbone DegradationThe upstream ISP failure has been mitigated by rerouting all traffic around that provider.3h 5mResolved
Aug 25, 2026[Deepgram EU API] Flux-Multi STT OutageResolved Between 07:13 and 09:00 UTC, flux-general-multi Speech-to-Text requests on api.eu.deepgram.com failed shortly after the WebSocket connection was established, returning an internal server error on the first…-661 minResolved
Aug 25, 2026[Deepgram API] Elevated Streaming STT Error RatesBetween 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…-1061 minResolved
Aug 20, 2026Elevated 5XX Error Rate for v1/auth/grantThis incident has been resolved.21 minResolved
Aug 13, 2026Elevated 5XX Error Rate for v1/auth/grantWe've resolved the issue and the service is back to normal.12 minResolved
Aug 4, 2026[Deepgram API] Elevated Batch and Streaming STT Error RatesThis incident has been resolved.3h 39mResolved
Jul 28, 2026[Deepgram API] Elevated Batch Error Rates: 400 error code responsesThis incident has been resolved.23h 7mResolved
Jul 24, 2026Intermittent Connectivity Issues Due to AWS US-WEST-2 Infrastructure EventThis incident has been resolved.4 minResolved
Jul 21, 2026Voice Agent API: Google/Gemini LLM errorsThis incident has been resolved.1h 34mResolved
Jul 7, 2026Elevated 5XX Errors for Flux STT RequestsThis incident has been resolved.2h 23mResolved
Jun 24, 2026ISP Network-Related IssueAn upstream ISP issue may have caused intermittent WebSocket connection failures, handshake timeouts, and degraded streaming connectivity. Incident time: 01:10 - 01:52 UTC-795 minResolved
Jun 23, 2026Voice Agent third-party provider Instability (Anthropic LLMs)Anthropic has resolved this incident. Incident end time: Jun 23, 2026, 16:44 UTC2h 16mResolved
Jun 18, 2026Degraded performance on Nova streaming STTNova-3 and Nova-2 streaming STT experienced elevated websocket connection errors and websocket disconnections between 13:00 - 16:00 UTC.-522 minResolved
Jun 17, 2026400 errors with PreRecorded STT ("REMOTE_CONTENT_ERROR" / "failed to return valid data") when passing a URLThe issue was resolved at 19:47 UTC.6h 12mResolved
Jun 17, 2026Elevated errors when using Google Gemini models with Voice AgentThis incident has been resolved.15h 0mResolved
Jun 15, 2026Degraded performance — Flux streaming Speech-to-TextThis 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…26h 59mResolved
May 22, 2026Outbound networking issues affecting STT, TTS streaming and batch serviceSome 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.0 minResolved
May 18, 2026Voice Agent - Elevated 4xx Error RatesBetween 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.-90 minResolved
May 14, 2026Elevated 5XX Errors for Non-English Batch STT Requests with RedactionThis issue has been resolved.8 minResolved
May 12, 2026Intermittent 404 HTTP errors Batch STT EnglishThis incident has been resolved.1h 48mResolved
May 11, 2026Voice Agent third-party provider instability (ChatGPT 4o)This incident has been resolved.24h 19mResolved
Apr 27, 2026Outbound networking issues affecting STT fetch requests and callbacks, Dashboard API requests, and Voice Agent 3rd party providersA 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. The majority…-38 minResolved
Apr 24, 2026Voice Agent third-party provider instability (Claude Sonnet 4.5)This incident has been resolved.180h 37mResolved
Apr 21, 2026Voice Agent third-party provider instability (Google Gemini LLMs)This incident has been resolved.242h 21mResolved
Apr 17, 2026Issues with downstream LLM provider in Voice Agent APIThis incident has been resolved.6h 52mResolved
Apr 10, 2026Outbound 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)This incident has been resolved.74h 19mResolved
Apr 6, 2026Issues with downstream LLM provider in Voice Agent APIWe are seeing elevated error rates and latency when using NVIDIA Llama Nemotron Super 49B (llama-nemotron-super-49B) as the managed LLM in Voice Agent API. To avoid downtime, please define multiple LLM providers…2858h 50mResolved
Mar 25, 2026Degraded API PerformanceBetween 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.0 minResolved
Mar 20, 2026Voice Agent API Degraded ServiceThis incident has been resolved74h 0mResolved
Mar 18, 2026Voice Agent API Degraded PerformanceThis incident has been resolved.1h 59mResolved
Mar 5, 2026Issues with downstream LLM provider in Voice Agent APIThis incident has been resolved.26 minResolved
Feb 26, 2026[Deepgram API] Elevated Errors for Streaming STTThis incident has been resolved.8h 49mResolved
Feb 24, 2026[Deepgram API] Flux SDK Session DisruptionsA temporary issue during a Flux-related update caused intermittent SDK session errors. The issue was identified and resolved. 2:00 AM UTC - 13:45 UTC0 minResolved
Feb 23, 2026Issues with downstream LLM provider in Voice Agent APIThe 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.20h 29mResolved
Feb 17, 2026Issues with downstream LLM provider in Voice Agent APIAs of 10:00 UTC, the issues from OpenAI models is being resolved.4h 1mResolved
Feb 16, 2026Issues with downstream LLM provider in Voice Agent APIThis incident has been resolved.6h 24mResolved
Feb 12, 2026Issues with downstream LLM provider in Voice Agent APIThe incident has been resolved.27h 41mResolved
Feb 4, 2026Issues with downstream LLM provider in Voice Agent APIThe downstream provider indicated the issue was resolved. There was an outage between 16:20 UTC / 8:20 PT and 16:55 UTC / 8:55 PT1h 54mResolved
Feb 3, 2026Issues with downstream LLM provider in Voice Agent APIThe incident has been resolved. The downstream provider's status page indicates the issues were resolved at 9:56 PT / 17:56 UTC7h 59mResolved
Jan 28, 2026Elevated Connection ErrorsThis incident has been resolved.188h 46mResolved
Jan 22, 2026Degraded Transcripts on Nova-3 Multilingual STT ModelFrom 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.0 minResolved
Dec 10, 2025[Deepgram API] Elevated Streaming Error Rates: 400 error code responsesThis incident has been resolved.29 minResolved
Nov 26, 2025Shai-Hulud 2.0 Supply Chain Incident – No Customer ImpactInformational (No Customer Action Required) Deepgram identified that our internal development environment was affected as part of the industry-wide Shai-Hulud 2.0 NPM supply chain attack. The attack used compromised…0 minResolved
Nov 14, 2025Elevated API ErrorsThis incident has been resolved.93h 22mResolved
Nov 13, 2025Elevated latency and connection timeouts on Deepgram servicesThis incident has been resolved.1h 56mResolved
Oct 29, 2025Outage for non-English batch speech-to-text requests utilizing redaction featureThis issue has been resolved.9h 18mResolved
Oct 28, 2025Increased Latency Over Streaming STT and Voice Agent APIThis issue has been resolved.2h 17mResolved
Oct 22, 2025Downstream third-party provider outage (OpenAI LLMs)As of 19:28 UTC OpenAI's LLMs are no longer returning 500 errors. We are still in conversation with OpenAI about what happened.173h 18mResolved

Hear about the next one while it is open

Everything above is a record written after the fact. We can email you when the next Deepgram incident opens instead, at the point where knowing still changes what you do.

Free, no password, no card. Unsubscribe in one click.

How to Read This Deepgram Incident Log

Each row is an incident PulsAPI observed, not a summary written afterwards. The duration is wall-clock time between the first failing check and the first clean one, so it includes the window before Deepgram acknowledged anything. Vendor post-mortems typically measure from acknowledgement, which is why their numbers are usually shorter.

Incidents still open have no duration yet and are listed as ongoing rather than being given a running total. The archive covers the last 365 days; anything older has aged out of the window rather than never having happened.

The longest single Deepgram outage in this window ran 119d 2h, against a mean recovery of 3d 13h. If you depend on Deepgram in a customer-facing path, the longest figure is the one to design around. The mean is what happens on a normal bad day; the maximum is what happens on the worst one.