Deepgram

Affected: TTS API

Failure mode: The text does not say enough to tell. Root cause: The vendor does not say why it happened. Tagged by claude-haiku-5-5 with low confidence (taxonomy v0.2).

1. investigating 2026-10-14 19:29 UTC

   We're seeing elevated 503 error rate for batch request to Flux TTS /v2/speak endpoint.

2. resolved 2026-10-14 21:00 UTC

   This issue has been resolved.

Excerpts are shortened. Read the full incident on Deepgram's status page.

Affected: TTS API

Failure mode: The text does not say enough to tell. Root cause: The vendor does not say why it happened. Tagged by claude-haiku-5-5 with low confidence (taxonomy v0.2).

1. investigating 2026-10-13 17:58 UTC

   We're investigating an issue where some Aura-2 requests failed with HTTP 503 error.

2. resolved 2026-10-13 18:09 UTC

   This issue has been resolved.

Excerpts are shortened. Read the full incident on Deepgram's status page.

Affected: TTS API

Failure mode: The text does not say enough to tell. Root cause: The vendor does not say why it happened. Tagged by claude-haiku-5-5 with medium confidence (taxonomy v0.2).

1. investigating 2026-10-08 02:58 UTC

   We are experiencing elevated error rates for Flux TTS.

2. resolved 2026-10-08 04:25 UTC

   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.

Excerpts are shortened. Read the full incident on Deepgram's status page.

Affected: TTS API

Failure mode: The text does not say enough to tell. Root cause: The vendor does not say why it happened. Tagged by claude-haiku-5-5 with medium confidence (taxonomy v0.2).

1. investigating 2026-10-05 09:55 UTC

   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.

2. monitoring 2026-10-05 11:40 UTC

   A fix has been implemented and we are monitoring the results.

3. resolved 2026-10-05 11:55 UTC

   This incident has been resolved.

Excerpts are shortened. Read the full incident on Deepgram's status page.

Affected: TTS API

Failure mode: The text does not say enough to tell. Root cause: The vendor does not say why it happened. Tagged by claude-haiku-5-5 with low confidence (taxonomy v0.2).

1. investigating 2026-10-03 15:52 UTC

   We are investigating elevated error rates for some Flux Text-to-Speech streaming requests in the US, beginning around 15:52 UTC. Affected users may see connections close unexpectedly with a 1011 / NET-0000 error.

2. identified 2026-10-03 17:46 UTC

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

3. resolved 2026-10-03 17:52 UTC

   This incident has been resolved.

Excerpts are shortened. Read the full incident on Deepgram's status page.

Affected: Batch API, Streaming API, TTS API, Voice Agent API

Failure mode: Login, tokens, certificates or credentials failed. Root cause: A human mistake during operations. Tagged by claude-haiku-5-5 with medium confidence (taxonomy v0.2).

1. investigating 2026-09-30 19:29 UTC

   We are investigating elevated error rates on API requests to US endpoints. Some requests and connections are failing with HTTP 500 errors or timing out.

2. resolved 2026-09-30 19:39 UTC

   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. Services have recovered automatically and this issue is resolved.

Excerpts are shortened. Read the full incident on Deepgram's status page.

Affected: Batch API

Failure mode: Exhausted memory, disk, CPU, queues, connection pools or quotas. Root cause: The vendor does not say why it happened. Tagged by claude-haiku-5-5 with medium confidence (taxonomy v0.2).

1. investigating 2026-09-28 17:40 UTC

   We are investigating elevated latency and 429 errors affecting some pre-recorded (batch) STT requests.

2. resolved 2026-09-28 17:53 UTC

   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 the issue, service has returned to normal.

Excerpts are shortened. Read the full incident on Deepgram's status page.

Affected: Streaming API

Failure mode: The text does not say enough to tell. Root cause: The vendor does not say why it happened. Tagged by claude-haiku-5-5 with medium confidence (taxonomy v0.2).

1. investigating 2026-09-28 17:04 UTC

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

2. resolved 2026-09-28 17:07 UTC

   This incident has been resolved.

Excerpts are shortened. Read the full incident on Deepgram's status page.

Affected: TTS API

Failure mode: The text does not say enough to tell. Root cause: The vendor does not say why it happened. Tagged by claude-haiku-5-5 with low confidence (taxonomy v0.2).

1. investigating 2026-09-25 09:45 UTC

   We are investigating elevated Flux TTS 1011 NET-1000 error rate in Deepgram global endpoint (api.deepgram.com). Regional endpoints (EU, India, Australia) are unaffected.

2. resolved 2026-09-25 13:44 UTC

   This issue has been resolved.

Excerpts are shortened. Read the full incident on Deepgram's status page.

Affected: TTS API

Failure mode: The text does not say enough to tell. Root cause: The vendor does not say why it happened. Tagged by claude-haiku-5-5 with medium confidence (taxonomy v0.2).

1. investigating 2026-09-22 12:10 UTC

   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.

2. resolved 2026-09-22 12:50 UTC

   The issue has been resolved.

Excerpts are shortened. Read the full incident on Deepgram's status page.

Failure mode: A provider or third-party service this vendor depends on failed. Root cause: A failure at a provider or vendor they depend on. Tagged by claude-haiku-5-5 with high confidence (taxonomy v0.2).

1. identified 2026-09-02 20:22 UTC

   Cogent is experiencing a backbone networking issue in LA, due to two fiber cuts. This is likely impacting a large majority of traffic flowing to the east-coast, we're looking into possible mitigations and Cogent has engineers actively working on it....

2. resolved 2026-09-02 23:28 UTC

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

Excerpts are shortened. Read the full incident on Deepgram's status page.

Failure mode: The text does not say enough to tell. Root cause: The vendor does not say why it happened. Tagged by claude-haiku-5-5 with medium confidence (taxonomy v0.2).

1. resolved 2026-08-25 07:00 UTC

   Resolved 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 audio and closing the connection. Affected clients saw abnormal...

Excerpts are shortened. Read the full incident on Deepgram's status page.

Failure mode: A zone, region or data center became unavailable. Root cause: A human mistake during operations. Tagged by claude-haiku-5-5 with medium confidence (taxonomy v0.2).

1. resolved 2026-08-24 23:00 UTC

   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. Traffic to the new site had been intentionally limited to...

Excerpts are shortened. Read the full incident on Deepgram's status page.

Affected: Developer Console, Management APIs

Failure mode: Login, tokens, certificates or credentials failed. Root cause: The vendor does not say why it happened. Tagged by claude-haiku-5-5 with medium confidence (taxonomy v0.2).

1. investigating 2026-08-20 15:52 UTC

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

2. monitoring 2026-08-20 16:45 UTC

   A fix has been implemented and we are monitoring the results.

3. resolved 2026-08-20 17:00 UTC

   This incident has been resolved.

Excerpts are shortened. Read the full incident on Deepgram's status page.

Affected: Management APIs

Failure mode: Login, tokens, certificates or credentials failed. Root cause: The vendor does not say why it happened. Tagged by claude-haiku-5-5 with medium confidence (taxonomy v0.2).

1. investigating 2026-08-13 13:17 UTC

   We're seeing elevated 503 error for v1/auth/grant endpoint.

2. resolved 2026-08-13 13:30 UTC

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

Excerpts are shortened. Read the full incident on Deepgram's status page.

Affected: Batch API, Streaming API

Failure mode: Network, DNS, routing or connectivity failure. Root cause: A failure at a provider or vendor they depend on. Tagged by claude-haiku-5-5 with high confidence (taxonomy v0.2).

1. investigating 2026-08-04 14:30 UTC

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

2. monitoring 2026-08-04 15:21 UTC

   An ISP network failure resulted in poor performance along one network path, resulting in degraded performance that primarily affected STT traffic. All network traffic is now routed through a high quality network path and services have recovered. We are actively monitoring.

3. resolved 2026-08-04 18:10 UTC

   This incident has been resolved.

Excerpts are shortened. Read the full incident on Deepgram's status page.

Affected: Batch API, Streaming API, TTS API

Failure mode: A provider or third-party service this vendor depends on failed. Root cause: The vendor does not say why it happened. Tagged by claude-haiku-5-5 with low confidence (taxonomy v0.2).

1. investigating 2026-07-28 14:00 UTC

   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.

2. investigating 2026-07-28 15:57 UTC

   We are continuing to investigate this issue.

3. monitoring 2026-07-28 15:57 UTC

   A fix has been implemented and we are monitoring the results.

4. monitoring 2026-07-28 15:58 UTC

   We are continuing to monitor for any further issues.

5. investigating 2026-07-28 16:03 UTC

   We are continuing to investigate an issue. STT batch requests may have returned 5xx errors, and some STT websockets may have experienced high latency, starting at 16:03 UTC.

6. monitoring 2026-07-28 16:34 UTC

   A fix has been implemented and traffic has returned to normal. We are monitoring the results.

7. resolved 2026-07-29 13:08 UTC

   This incident has been resolved.

Excerpts are shortened. Read the full incident on Deepgram's status page.

Failure mode: A provider or third-party service this vendor depends on failed. Root cause: A failure at a provider or vendor they depend on. Tagged by claude-haiku-5-5 with high confidence (taxonomy v0.2).

Names an upstream provider: AWS.

1. investigating 2026-07-24 13:18 UTC

   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 elevated errors, connection timeouts, and...

2. resolved 2026-07-24 13:22 UTC

   This incident has been resolved.

Excerpts are shortened. Read the full incident on Deepgram's status page.

Affected: Voice Agent API: Downstream Providers

Failure mode: A code release introduced the failure. Root cause: A bug in the vendor's own code. Tagged by claude-haiku-5-5 with high confidence (taxonomy v0.2).

1. investigating 2026-07-21 13:45 UTC

   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. Two Gemini models were unaffected; all other providers and products were unaffected. The...

2. resolved 2026-07-21 15:20 UTC

   This incident has been resolved.

Excerpts are shortened. Read the full incident on Deepgram's status page.

Affected: Streaming API

Failure mode: The text does not say enough to tell. Root cause: The vendor does not say why it happened. Tagged by claude-haiku-5-5 with medium confidence (taxonomy v0.2).

1. investigating 2026-07-07 15:56 UTC

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

2. resolved 2026-07-07 18:20 UTC

   This incident has been resolved.

Excerpts are shortened. Read the full incident on Deepgram's status page.

Failure mode: A provider or third-party service this vendor depends on failed. Root cause: A failure at a provider or vendor they depend on. Tagged by claude-haiku-5-5 with medium confidence (taxonomy v0.2).

1. resolved 2026-06-24 01:00 UTC

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

Excerpts are shortened. Read the full incident on Deepgram's status page.

Affected: Voice Agent API: Downstream Providers

Failure mode: A provider or third-party service this vendor depends on failed. Root cause: A failure at a provider or vendor they depend on. Tagged by claude-haiku-5-5 with high confidence (taxonomy v0.2).

Names an upstream provider: Anthropic (Claude).

1. monitoring 2026-06-23 15:06 UTC

   We are currently observing elevated error rates from our downstream third-party provider, Anthropic. Deepgram infrastructure, including our canaries, remains healthy. Incident start time: Jun 23, 2026, 14:19 UTC (Anthropic status updates: https://status.claude.com)

2. resolved 2026-06-23 17:22 UTC

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

Excerpts are shortened. Read the full incident on Deepgram's status page.

Failure mode: Network, DNS, routing or connectivity failure. Root cause: The vendor does not say why it happened. Tagged by claude-haiku-5-5 with low confidence (taxonomy v0.2).

1. resolved 2026-06-18 13:00 UTC

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

Excerpts are shortened. Read the full incident on Deepgram's status page.

Affected: Voice Agent API: Downstream Providers

Failure mode: A provider or third-party service this vendor depends on failed. Root cause: A failure at a provider or vendor they depend on. Tagged by claude-haiku-5-5 with high confidence (taxonomy v0.2).

1. investigating 2026-06-17 18:00 UTC

   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...

2. identified 2026-06-17 20:54 UTC

   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...

3. identified 2026-06-17 20:55 UTC

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

4. resolved 2026-06-18 04:00 UTC

   This incident has been resolved.

Excerpts are shortened. Read the full incident on Deepgram's status page.

Affected: Batch API

Failure mode: The text does not say enough to tell. Root cause: The vendor does not say why it happened. Tagged by claude-haiku-5-5 with medium confidence (taxonomy v0.2).

1. identified 2026-06-17 13:35 UTC

   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...

2. resolved 2026-06-17 19:47 UTC

   The issue was resolved at 19:47 UTC.

Excerpts are shortened. Read the full incident on Deepgram's status page.

Affected: Streaming API

Failure mode: Orchestration, control plane, service discovery or load balancing failed. Root cause: The vendor does not say why it happened. Tagged by claude-haiku-5-5 with medium confidence (taxonomy v0.2).

1. investigating 2026-06-15 11:00 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...

2. identified 2026-06-16 13:00 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.

3. resolved 2026-06-16 14:00 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...

Excerpts are shortened. Read the full incident on Deepgram's status page.

Affected: Batch API, Streaming API, TTS API

Failure mode: Network, DNS, routing or connectivity failure. Root cause: The vendor does not say why it happened. Tagged by claude-haiku-5-5 with medium confidence (taxonomy v0.2).

1. resolved 2026-05-22 21:00 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.

Excerpts are shortened. Read the full incident on Deepgram's status page.

Failure mode: A code release introduced the failure. Root cause: A bug in the vendor's own code. Tagged by claude-haiku-5-5 with medium confidence (taxonomy v0.2).

1. resolved 2026-05-18 22:06 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.

Excerpts are shortened. Read the full incident on Deepgram's status page.

Affected: Batch API

Failure mode: The text does not say enough to tell. Root cause: The vendor does not say why it happened. Tagged by claude-haiku-5-5 with low confidence (taxonomy v0.2).

1. investigating 2026-05-14 18:52 UTC

   We are currently investigating an increase in 5XX errors for non-English STT requests that are using redaction.

2. resolved 2026-05-14 19:00 UTC

   This issue has been resolved.

Excerpts are shortened. Read the full incident on Deepgram's status page.

Affected: Batch API

Failure mode: The text does not say enough to tell. Root cause: The vendor does not say why it happened. Tagged by claude-haiku-5-5 with low confidence (taxonomy v0.2).

1. investigating 2026-05-12 16:18 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...

2. resolved 2026-05-12 18:07 UTC

   This incident has been resolved.

Excerpts are shortened. Read the full incident on Deepgram's status page.

Affected: Voice Agent API: Downstream Providers

Failure mode: A provider or third-party service this vendor depends on failed. Root cause: A failure at a provider or vendor they depend on. Tagged by claude-haiku-5-5 with high confidence (taxonomy v0.2).

Names an upstream provider: OpenAI.

1. identified 2026-05-11 16:35 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.

2. resolved 2026-05-12 16:55 UTC

   This incident has been resolved.

Excerpts are shortened. Read the full incident on Deepgram's status page.

Affected: Batch API, Streaming API, Voice Agent API

Failure mode: Network, DNS, routing or connectivity failure. Root cause: The vendor does not say why it happened. Tagged by claude-haiku-5-5 with medium confidence (taxonomy v0.2).

1. resolved 2026-04-27 14:14 UTC

   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. The majority of customers were unaffected.

Excerpts are shortened. Read the full incident on Deepgram's status page.

Affected: Voice Agent API: Downstream Providers

Failure mode: A provider or third-party service this vendor depends on failed. Root cause: A failure at a provider or vendor they depend on. Tagged by claude-haiku-5-5 with high confidence (taxonomy v0.2).

Names an upstream provider: Anthropic (Claude).

1. investigating 2026-04-24 05:45 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.

2. resolved 2026-05-01 18:22 UTC

   This incident has been resolved.

Excerpts are shortened. Read the full incident on Deepgram's status page.

Affected: Voice Agent API: Downstream Providers

Failure mode: A provider or third-party service this vendor depends on failed. Root cause: A failure at a provider or vendor they depend on. Tagged by claude-haiku-5-5 with high confidence (taxonomy v0.2).

1. identified 2026-04-21 15:59 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...

2. resolved 2026-05-01 18:21 UTC

   This incident has been resolved.

Excerpts are shortened. Read the full incident on Deepgram's status page.

Affected: Voice Agent API

Failure mode: A provider or third-party service this vendor depends on failed. Root cause: A failure at a provider or vendor they depend on. Tagged by claude-haiku-5-5 with high confidence (taxonomy v0.2).

Names an upstream provider: OpenAI.

1. investigating 2026-04-17 20:56 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.

2. investigating 2026-04-18 03:48 UTC

   We are continuing to investigate this issue.

3. resolved 2026-04-18 03:48 UTC

   This incident has been resolved.

Excerpts are shortened. Read the full incident on Deepgram's status page.

Affected: Batch API, TTS API, Voice Agent API, Voice Agent API: Downstream Providers

Failure mode: Network, DNS, routing or connectivity failure. Root cause: Network or DNS. Tagged by claude-haiku-5-5 with high confidence (taxonomy v0.2).

1. identified 2026-04-10 17:27 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...

2. monitoring 2026-04-10 18:15 UTC

   A network infrastructure fix was implemented at 18:15 UTC and the behavior was immediately resolved. We are continuing to monitor carefully.

3. resolved 2026-04-13 19:47 UTC

   This incident has been resolved.

Excerpts are shortened. Read the full incident on Deepgram's status page.

Failure mode: The text does not say enough to tell. Root cause: The vendor does not say why it happened. Tagged by claude-haiku-5-5 with medium confidence (taxonomy v0.2).

1. resolved 2026-03-25 15:16 UTC

   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.

Excerpts are shortened. Read the full incident on Deepgram's status page.

Affected: Voice Agent API: Downstream Providers

Failure mode: A provider or third-party service this vendor depends on failed. Root cause: A failure at a provider or vendor they depend on. Tagged by claude-haiku-5-5 with high confidence (taxonomy v0.2).

Names an upstream provider: OpenAI.

1. investigating 2026-03-20 16:53 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.

2. resolved 2026-03-23 18:53 UTC

   This incident has been resolved

Excerpts are shortened. Read the full incident on Deepgram's status page.

Affected: Voice Agent API: Downstream Providers

Failure mode: A provider or third-party service this vendor depends on failed. Root cause: A failure at a provider or vendor they depend on. Tagged by claude-haiku-5-5 with high confidence (taxonomy v0.2).

Names an upstream provider: OpenAI.

1. identified 2026-03-18 15:00 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.

2. identified 2026-03-18 15:30 UTC

   We are continuing to monitor this issue.

3. resolved 2026-03-18 17:00 UTC

   This incident has been resolved.

Excerpts are shortened. Read the full incident on Deepgram's status page.

Affected: Voice Agent API: Downstream Providers

Failure mode: A provider or third-party service this vendor depends on failed. Root cause: A failure at a provider or vendor they depend on. Tagged by claude-haiku-5-5 with high confidence (taxonomy v0.2).

Names an upstream provider: OpenAI.

1. identified 2026-03-05 00:59 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.

2. resolved 2026-03-05 01:26 UTC

   This incident has been resolved.

Excerpts are shortened. Read the full incident on Deepgram's status page.

Affected: Streaming API

Failure mode: Exhausted memory, disk, CPU, queues, connection pools or quotas. Root cause: The vendor does not say why it happened. Tagged by claude-haiku-5-5 with low confidence (taxonomy v0.2).

1. investigating 2026-02-26 17:16 UTC

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

2. monitoring 2026-02-26 20:57 UTC

   We are monitoring the issue.

3. resolved 2026-02-27 02:05 UTC

   This incident has been resolved.

Excerpts are shortened. Read the full incident on Deepgram's status page.

Failure mode: A code release introduced the failure. Root cause: The vendor does not say why it happened. Tagged by claude-haiku-5-5 with medium confidence (taxonomy v0.2).

1. resolved 2026-02-24 02:00 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

Excerpts are shortened. Read the full incident on Deepgram's status page.

Affected: Voice Agent API, Voice Agent API: Downstream Providers

Failure mode: A provider or third-party service this vendor depends on failed. Root cause: A failure at a provider or vendor they depend on. Tagged by claude-haiku-5-5 with high confidence (taxonomy v0.2).

Names an upstream provider: Anthropic (Claude).

1. identified 2026-02-23 17:58 UTC

   There is an ongoing Anthropic 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. The incident started at...

2. resolved 2026-02-24 14:28 UTC

   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.

Excerpts are shortened. Read the full incident on Deepgram's status page.

Affected: Voice Agent API

Failure mode: A provider or third-party service this vendor depends on failed. Root cause: A failure at a provider or vendor they depend on. Tagged by claude-haiku-5-5 with high confidence (taxonomy v0.2).

Names an upstream provider: OpenAI.

1. investigating 2026-02-17 16:15 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, including at least one...

2. resolved 2026-02-17 20:16 UTC

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

Excerpts are shortened. Read the full incident on Deepgram's status page.

Affected: Voice Agent API, Voice Agent API: Downstream Providers

Failure mode: A provider or third-party service this vendor depends on failed. Root cause: A failure at a provider or vendor they depend on. Tagged by claude-haiku-5-5 with high confidence (taxonomy v0.2).

Names an upstream provider: OpenAI.

1. investigating 2026-02-16 17:08 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, including at least one...

2. investigating 2026-02-16 17:08 UTC

   We are continuing to investigate this issue.

3. resolved 2026-02-16 23:32 UTC

   This incident has been resolved.

Excerpts are shortened. Read the full incident on Deepgram's status page.

Affected: Voice Agent API: Downstream Providers

Failure mode: A provider or third-party service this vendor depends on failed. Root cause: A failure at a provider or vendor they depend on. Tagged by claude-haiku-5-5 with high confidence (taxonomy v0.2).

Names an upstream provider: OpenAI.

1. investigating 2026-02-12 17:47 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, including at least one...

2. resolved 2026-02-13 21:28 UTC

   The incident has been resolved.

Excerpts are shortened. Read the full incident on Deepgram's status page.

Affected: Voice Agent API, Voice Agent API: Downstream Providers

Failure mode: A provider or third-party service this vendor depends on failed. Root cause: A failure at a provider or vendor they depend on. Tagged by claude-haiku-5-5 with high confidence (taxonomy v0.2).

Names an upstream provider: Anthropic (Claude).

1. identified 2026-02-04 16:52 UTC

   We are currently seeing elevated error rates from Anthropic 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, including at least one...

2. resolved 2026-02-04 18:47 UTC

   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

Excerpts are shortened. Read the full incident on Deepgram's status page.

Affected: Voice Agent API, Voice Agent API: Downstream Providers

Failure mode: A provider or third-party service this vendor depends on failed. Root cause: A failure at a provider or vendor they depend on. Tagged by claude-haiku-5-5 with high confidence (taxonomy v0.2).

Names an upstream provider: Anthropic (Claude).

1. identified 2026-02-03 15:35 UTC

   We are currently seeing elevated error rates from Anthropic 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, including at least one...

2. monitoring 2026-02-03 15:55 UTC

   Failures have reduced since 15:55UTC, we are monitoring the downstream provider's status page.

3. monitoring 2026-02-03 20:40 UTC

   We are continuing to monitor for any further issues with the downstream provider.

4. resolved 2026-02-03 23:35 UTC

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

Excerpts are shortened. Read the full incident on Deepgram's status page.

Affected: Batch API, Streaming API

Failure mode: The text does not say enough to tell. Root cause: The vendor does not say why it happened. Tagged by claude-haiku-5-5 with low confidence (taxonomy v0.2).

1. monitoring 2026-01-28 22:10 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.

2. investigating 2026-01-29 21:18 UTC

   We're observing elevated connection error rates at the moment, and we're actively investigating the issue.

3. investigating 2026-01-29 21:19 UTC

   We are continuing to investigate this issue.

4. investigating 2026-01-30 17:04 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.

5. investigating 2026-02-02 17:52 UTC

   We are continuing to investigate this issue.

6. monitoring 2026-02-03 01:16 UTC

   A fix has been implemented and we are monitoring the results.

7. monitoring 2026-02-04 23:21 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...

8. resolved 2026-02-05 18:56 UTC

   This incident has been resolved.

Excerpts are shortened. Read the full incident on Deepgram's status page.

Failure mode: AI model returned degraded, wrong or empty output (not errors or timeouts). Root cause: A model or AI component. Tagged by claude-haiku-5-5 with high confidence (taxonomy v0.2).

1. resolved 2026-01-22 23:45 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.

Excerpts are shortened. Read the full incident on Deepgram's status page.