Deepgram Voice AI Outage History
Deepgram Voice AI is up right nowPingoru has recorded 62 incidents for Deepgram Voice AI: 60 in the last 12 months and 20 in the last 90 days.
Show as a table
| Month | Incidents | Hours with an open incident |
|---|---|---|
| April 2026 | 5 | 305 of 720 (42%) |
| May 2026 | 6 | 48 of 744 (6%) |
| June 2026 | 6 | 48 of 720 (7%) |
| July 2026 | 4 | 27 of 744 (4%) |
| August 2026 | 5 | 10 of 744 (1%) |
| September 2026 | 7 | 8 of 720 (1%) |
| October 2026 | 7 | 26 of 591 (4%) |
Incidents, newest first
Minor June 17, 2026 400 errors with PreRecorded STT ("REMOTE_CONTENT_ERROR" / "failed to return valid data") when passing a URL 6h 12m Batch API
Started Jun 17, 2026, 01:35 PM UTC· resolved Jun 17, 2026, 07:47 PM UTC
- identified Jun 23, 2026, 08:38 PM UTC
Between the hours of 13:35 UTC - 12:47 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.
- resolved Jun 23, 2026, 08:38 PM UTC
The issue was resolved at 19:47 UTC.
Minor June 15, 2026 Degraded performance — Flux streaming Speech-to-Text 1d 2h Streaming API
Started Jun 15, 2026, 11:00 AM UTC· resolved Jun 16, 2026, 02:00 PM UTC
- investigating Jun 17, 2026, 07:02 PM UTC
Some streaming Speech-to-Text connections on the Flux model established successfully but then terminated a few seconds into the session due to an internal error, before returning a final transcript. Applications relying on final transcripts (e.g. IVR/voice-agent flows) would have seen sessions open with no transcript returned.
- identified Jun 17, 2026, 07:04 PM UTC
We identified a degradation affecting a subset of Flux streaming Speech-to-Text sessions, where connections terminated before returning a transcript. We've isolated it to specific degraded hosts and are mitigating.
- resolved Jun 17, 2026, 07:13 PM UTC
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. We're continuing to monitor and apologize for the disruption.
Notice May 22, 2026 Outbound networking issues affecting STT, TTS streaming and batch service – Batch API, Streaming API, TTS API
Started May 22, 2026, 09:00 PM UTC· resolved May 22, 2026, 09:00 PM UTC
- resolved May 22, 2026, 09:00 PM UTC
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.
Notice May 22, 2026 Degraded API Performance 11m
Started May 22, 2026, 05:59 PM UTC· resolved May 22, 2026, 06:10 PM UTC
- monitoring May 22, 2026, 05:59 PM UTC
Some API requests may have experienced increased latency and elevated error rates for approximately 30 minutes starting at 16:40 UTC on May 22, 2026. The issue has been identified and is being resolved.
Minor May 18, 2026 Voice Agent - Elevated 4xx Error Rates 6m
Started May 18, 2026, 10:06 PM UTC· resolved May 18, 2026, 10:12 PM UTC
- resolved May 18, 2026, 11:36 PM UTC
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.
Minor May 14, 2026 Elevated 5XX Errors for Non-English Batch STT Requests with Redaction 4h 8m Batch API
Started May 14, 2026, 02:52 PM UTC· resolved May 14, 2026, 07:00 PM UTC
- investigating May 14, 2026, 07:08 PM UTC
We are currently investigating an increase in 5XX errors for non-English STT requests that are using redaction.
- resolved May 14, 2026, 07:08 PM UTC
This issue has been resolved.
Minor May 12, 2026 Intermittent 404 HTTP errors Batch STT English 1h 48m Batch API
Started May 12, 2026, 04:18 PM UTC· resolved May 12, 2026, 06:07 PM UTC
- investigating May 12, 2026, 08:14 PM UTC
During the affected time period, some English batch speech-to-text requests intermittently returned 404 Not Found HTTP errors. This issue was limited to requests that met both of the following criteria: - Utilized English batch STT models (including both monolingual English and multilingual models that support English transcription) - Had Smart Format, Entity Detection, or Redaction features enabled.
- resolved May 12, 2026, 08:15 PM UTC
This incident has been resolved.
Minor May 11, 2026 Voice Agent third-party provider instability (ChatGPT 4o) 1d Voice Agent API: Downstream Providers
Started May 11, 2026, 04:35 PM UTC· resolved May 12, 2026, 04:55 PM UTC
- identified May 11, 2026, 04:35 PM UTC
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.
- resolved May 12, 2026, 04:55 PM UTC
This incident has been resolved.
Notice April 27, 2026 Outbound networking issues affecting STT fetch requests and callbacks, Dashboard API requests, and Voice Agent 3rd party providers – Batch API, Streaming API, Voice Agent API
Started Apr 27, 2026, 02:14 PM UTC· resolved Apr 27, 2026, 02:14 PM UTC
- resolved Apr 27, 2026, 02:52 PM UTC
This impacted STT fetch requests, callbacks, and voice Agent third-party providers. API calls that proxy to the console were also returning 503s intermittently.
Minor April 24, 2026 Voice Agent third-party provider instability (Claude Sonnet 4.5) 7d 12h Voice Agent API: Downstream Providers
Started Apr 24, 2026, 05:45 AM UTC· resolved May 01, 2026, 06:22 PM UTC
- investigating Apr 24, 2026, 05:45 AM UTC
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.
- resolved May 01, 2026, 06:22 PM UTC
This incident has been resolved.
Minor April 21, 2026 Voice Agent third-party provider instability (Google Gemini LLMs) 10d 2h Voice Agent API: Downstream Providers
Started Apr 21, 2026, 03:59 PM UTC· resolved May 01, 2026, 06:21 PM UTC
- identified Apr 21, 2026, 03:59 PM UTC
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.
- resolved May 01, 2026, 06:21 PM UTC
This incident has been resolved.
Notice April 17, 2026 Issues with downstream LLM provider in Voice Agent API 6h 52m Voice Agent API
Started Apr 17, 2026, 08:56 PM UTC· resolved Apr 18, 2026, 03:48 AM UTC
- investigating Apr 17, 2026, 08:56 PM 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.
- investigating Apr 18, 2026, 03:48 AM UTC
We are continuing to investigate this issue.
- resolved Apr 18, 2026, 03:48 AM UTC
This incident has been resolved.
Notice April 10, 2026 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) 3d 2h Batch API, TTS API, Voice Agent API, Voice Agent API: Downstream Providers
Started Apr 10, 2026, 05:27 PM UTC· resolved Apr 13, 2026, 07:47 PM UTC
- identified Apr 10, 2026, 05:27 PM UTC
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.
- monitoring Apr 10, 2026, 07:09 PM UTC
A network infrastructure fix was implemented at 18:15 UTC and the behavior was immediately resolved. We are continuing to monitor carefully.
- resolved Apr 13, 2026, 07:47 PM UTC
This incident has been resolved.
Minor March 20, 2026 Voice Agent API Degraded Service 3d 2h Voice Agent API: Downstream Providers
Started Mar 20, 2026, 04:53 PM UTC· resolved Mar 23, 2026, 06:53 PM UTC
- investigating Mar 20, 2026, 04:53 PM UTC
There is an ongoing OpenAI outage that is affecting our Voice Agent. 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.
- resolved Mar 23, 2026, 02:49 PM UTC
This incident has been resolved
Minor March 18, 2026 Voice Agent API Degraded Performance 1h 59m Voice Agent API: Downstream Providers
Started Mar 18, 2026, 03:00 PM UTC· resolved Mar 18, 2026, 05:00 PM UTC
- identified Mar 18, 2026, 04:48 PM UTC
There is an ongoing OpenAI outage that is affecting our Voice Agent. 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.
- identified Mar 18, 2026, 05:19 PM UTC
We are continuing to monitor this issue.
- resolved Mar 19, 2026, 01:36 AM UTC
This incident has been resolved.
Notice February 26, 2026 [Deepgram API] Elevated Errors for Streaming STT 8h 49m Streaming API
Started Feb 26, 2026, 05:16 PM UTC· resolved Feb 27, 2026, 02:05 AM UTC
- investigating Feb 26, 2026, 05:16 PM UTC
We are currently investigating an issue that results in increased Speech-to-Text result latency.
- monitoring Feb 26, 2026, 08:57 PM UTC
We are monitoring the issue.
- resolved Feb 27, 2026, 02:05 AM UTC
This incident has been resolved.
Notice February 24, 2026 [Deepgram API] Flux SDK Session Disruptions 11h 45m
Started Feb 24, 2026, 02:00 AM UTC· resolved Feb 24, 2026, 01:45 PM UTC
- resolved Feb 26, 2026, 08:25 PM UTC
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
Minor January 28, 2026 Elevated Connection Errors 7d 20h Batch API, Streaming API
Started Jan 28, 2026, 10:10 PM UTC· resolved Feb 05, 2026, 06:56 PM UTC
- monitoring Jan 28, 2026, 10:10 PM UTC
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.
- investigating Jan 29, 2026, 09:18 PM UTC
We're observing elevated connection error rates at the moment, and we're actively investigating the issue.
- investigating Jan 29, 2026, 09:19 PM UTC
We are continuing to investigate this issue.
- investigating Jan 30, 2026, 05:04 PM UTC
We're currently seeing elevated response time, as well as increased 429 errors for batch STT. We're actively working on mitigating the issue.
- investigating Feb 02, 2026, 05:52 PM UTC
We are continuing to investigate this issue.
- monitoring Feb 03, 2026, 01:16 AM UTC
A fix has been implemented and we are monitoring the results.
- monitoring Feb 04, 2026, 11:21 PM UTC
The implemented fixes have resulted in stable systems since 2026-02-03 17:35 UTC. We are continuing to monitor carefully. The issue primarily impacted STT batch services, with some impact on STT streaming. Specifically, response times and 429 errors increased for batch, and a percentage of connection errors occurred for both batch and streaming.
- resolved Feb 05, 2026, 06:56 PM UTC
This incident has been resolved.
Minor January 22, 2026 Degraded Transcripts on Nova-3 Multilingual STT Model 2h 45m
Started Jan 22, 2026, 09:00 PM UTC· resolved Jan 22, 2026, 11:45 PM UTC
- resolved Jan 26, 2026, 04:40 PM UTC
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.
Major December 10, 2025 [Deepgram API] Elevated Streaming Error Rates: 400 error code responses 29m Streaming API
Started Dec 10, 2025, 07:35 PM UTC· resolved Dec 10, 2025, 08:05 PM UTC
- identified Dec 10, 2025, 08:09 PM UTC
The issue has been identified and is being actively resolved.
- monitoring Dec 10, 2025, 09:01 PM UTC
A fix has been implemented and we are monitoring the results.
- resolved Dec 10, 2025, 09:02 PM UTC
This incident has been resolved.
Notice November 26, 2025 Shai-Hulud 2.0 Supply Chain Incident – No Customer Impact –
Started Nov 26, 2025, 12:00 AM UTC· resolved Nov 26, 2025, 12:00 AM UTC
- resolved Dec 04, 2025, 10:50 PM UTC
Informational (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 NPM packages to inject malicious CI/CD workflows and attempt to exfiltrate internal development credentials. Our investigation confirms: - No access to customer data or databases - No impact to production API infrastructure or service availability - No modification of published Deepgram SDKs or packages - No effect on customer authentication or API keys Timeline (UTC): - 00:41, Nov 26: Webhook alert on an internal GitHub repo; engineers link activity to Shai-Hulud 2.0, disable malicious workflows, and rotate exposed credentials. - 21:45, Nov 26: Additional commits via a compromised GitHub App publish some internal materials (no customer or production impact); the account is removed, GitHub Actions disabled, and the org moved into a locked-down state. We see no further signs of compromise and are gradually restoring normal operations while tightening SDLC and CI/CD controls. Customer action: None required. Questions: [email protected] • [email protected] This incident affected internal development infrastructure only; customer-facing APIs and services were not impacted.
Minor November 14, 2025 Elevated API Errors 3d 21h Batch API, Streaming API, TTS API, Voice Agent API
Started Nov 14, 2025, 07:10 PM UTC· resolved Nov 18, 2025, 04:33 PM UTC
- investigating Nov 14, 2025, 07:22 PM UTC
We're experiencing an elevated level of API errors and are currently looking into the issue.
- investigating Nov 14, 2025, 08:21 PM UTC
We are continuing to investigate this issue.
- investigating Nov 14, 2025, 11:44 PM UTC
We are still investigating the issue.
- identified Nov 15, 2025, 12:28 AM UTC
The issue has been identified and a fix is being implemented.
- monitoring Nov 15, 2025, 01:33 AM UTC
A fix has been implemented and we are monitoring the results.
- monitoring Nov 15, 2025, 01:42 AM UTC
We are continuing to monitor for any further issues.
- monitoring Nov 18, 2025, 04:28 PM UTC
We are continuing to monitor for any further issues.
- resolved Nov 18, 2025, 04:33 PM UTC
This incident has been resolved.
Minor November 13, 2025 Elevated latency and connection timeouts on Deepgram services 1h 56m Batch API, Streaming API, TTS API, Voice Agent API
Started Nov 13, 2025, 11:16 PM UTC· resolved Nov 14, 2025, 01:13 AM UTC
- investigating Nov 13, 2025, 11:16 PM UTC
We are investigating an issue causing elevated latency and connection timeouts to Deepgram services.
- monitoring Nov 13, 2025, 11:35 PM UTC
We have adjusted our networking and are seeing recovery.
- resolved Nov 14, 2025, 01:13 AM UTC
This incident has been resolved.
Major October 29, 2025 Outage for non-English batch speech-to-text requests utilizing redaction feature 9h 18m Batch API
Started Oct 29, 2025, 04:15 PM UTC· resolved Oct 30, 2025, 01:34 AM UTC
- investigating Oct 29, 2025, 05:33 PM UTC
We're experiencing an outage for our non-English batch speech-to-text requests utilizing redaction feature.
- monitoring Oct 29, 2025, 05:34 PM UTC
We've implemented a fix and are currently monitoring the status of the issue.
- monitoring Oct 29, 2025, 11:46 PM UTC
We are continuing to monitor for any further issues.
- resolved Oct 30, 2025, 01:34 AM UTC
This issue has been resolved.
Minor October 28, 2025 Increased Latency Over Streaming STT and Voice Agent API 2h 17m Streaming API, Voice Agent API
Started Oct 28, 2025, 02:02 PM UTC· resolved Oct 28, 2025, 04:20 PM UTC
- investigating Oct 28, 2025, 03:32 PM UTC
We are currently investigating increased latency over our streaming STT API and Voice Agent API.
- investigating Oct 28, 2025, 04:00 PM UTC
We identified a potential source of increased latency and are currently monitoring a mitigation step.
- monitoring Oct 28, 2025, 04:39 PM UTC
The increased latency issue has significantly improved. We will continue to monitor the performance.
- resolved Oct 28, 2025, 05:39 PM UTC
This issue has been resolved.