Is Deepgram down right now?
No, it is up
Operational · All Systems Operational
Components
- Deepgram Public API (api.deepgram.com) · Batch APIOperational
- Documentation · Developer DocumentationOperational
- On-Premise · License ValidationOperational
- Deepgram Public API (api.deepgram.com) · Streaming APIOperational
- On-Premise · Usage APIOperational
- Developer Console / Management APIs · Developer ConsoleOperational
- Documentation · Deepgram WebsiteOperational
- Deepgram Public API (api.deepgram.com) · TTS APIOperational
- Developer Console / Management APIs · API PlaygroundOperational
- Deepgram Public API (api.deepgram.com) · Voice Agent APIOperational
- Developer Console / Management APIs · Management APIsOperational
- Deepgram Public API (api.deepgram.com) · Voice Agent API: Downstream ProvidersOperational
- Deepgram Public API (api.deepgram.com) · DG Whisper CloudOperational
User reports
Having trouble with Deepgram? Reports are anonymous and only counted, no cookies.
Deepgram uptime, last 90 days
Each bar is one UTC day, coloured by the worst state we saw on the official status page.
Recent Deepgram incidents
Elevated errors from authentication services at one datacenter · 29 Oct 2026, 15:17 UTC · 55 min · minor
resolved · 29 Oct 2026, 16:12 UTC
Between 15:17 and 15:45 UTC on October 29, an issue with authentication services at one of our US datacenters caused some API requests and Voice Agent sessions to fail with 5xx errors, and some transcription callbacks sent from that datacenter to carry an invalid Dg-Token header. A fix was deployed at 15:45 UTC and error rates returned to normal. This incident is resolved. All systems are operational.
investigating · 29 Oct 2026, 15:17 UTC
We are investigating elevated errors with authentication services at one of our US datacenters. Some API requests and Voice Agent sessions routed there may fail with 5xx errors, and some transcription callbacks sent from that datacenter may carry an invalid Dg-Token header.
Elevated Latency and Errors for Batch STT · 22 Oct 2026, 19:27 UTC · 2 h 25 min · minor
resolved · 22 Oct 2026, 21:53 UTC
Between 19:27 and 21:53 UTC on October 22, some pre-recorded (batch) requests intermittently had elevated latency, and some timed out. This incident is resolved. All systems are operational.
investigating · 22 Oct 2026, 19:27 UTC
We are currently investigating elevated latency and 5xx error rates returned from batch requests to our API platform.
Elevated 5xx Errors · 22 Oct 2026, 16:00 UTC · 18 h 59 min · major
resolved · 23 Oct 2026, 11:00 UTC
Between 16:00 and 17:09 UTC on October 22, some API requests returned 5xx errors because of an issue with authentication services at one of our datacenters. This incident is resolved. All systems are operational.
monitoring · 22 Oct 2026, 17:29 UTC
We have identified the issue & are monitoring the solution.
investigating · 22 Oct 2026, 17:14 UTC
We are continuing to investigate this issue.
investigating · 22 Oct 2026, 16:00 UTC
We are currently investigating elevated 5xx errors with authentication services at one of our datacenters.
Elevated 503 errors for bath Flux TTS requests · 14 Oct 2026, 19:29 UTC · 1 h 31 min · minor
resolved · 14 Oct 2026, 21:00 UTC
This issue has been resolved.
investigating · 14 Oct 2026, 19:29 UTC
We're seeing elevated 503 error rate for batch request to Flux TTS /v2/speak endpoint.
Elevated 503 errors for Aura-2 TTS · 13 Oct 2026, 17:58 UTC · 11 min · minor
resolved · 13 Oct 2026, 18:09 UTC
This issue has been resolved.
investigating · 13 Oct 2026, 17:58 UTC
We're investigating an issue where some Aura-2 requests failed with HTTP 503 error.
Elevated error rates for Flux TTS · 8 Oct 2026, 02:58 UTC · 1 h 27 min · minor
resolved · 8 Oct 2026, 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.
investigating · 8 Oct 2026, 02:58 UTC
We are experiencing elevated error rates for Flux TTS.
Elevated errors for Flux TTS · 5 Oct 2026, 09:55 UTC · 2 h · minor
resolved · 5 Oct 2026, 11:55 UTC
This incident has been resolved.
monitoring · 5 Oct 2026, 11:40 UTC
A fix has been implemented and we are monitoring the results.
investigating · 5 Oct 2026, 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.
Elevated errors for Flux TTS · 3 Oct 2026, 15:52 UTC · 2 h 1 min · minor
resolved · 3 Oct 2026, 17:52 UTC
This incident has been resolved.
identified · 3 Oct 2026, 17:46 UTC
The issue has been identified and a fix is being implemented.
investigating · 3 Oct 2026, 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.
Elevated API errors · 30 Sept 2026, 19:29 UTC · 10 min · minor
resolved · 30 Sept 2026, 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.
investigating · 30 Sept 2026, 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.
Elevated Latency and Errors for Batch STT (US) · 28 Sept 2026, 17:53 UTC · minor
resolved · 28 Sept 2026, 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.
investigating · 28 Sept 2026, 17:40 UTC
We are investigating elevated latency and 429 errors affecting some pre-recorded (batch) STT requests.
Elevated latency on Flux STT (US) · 28 Sept 2026, 17:04 UTC · 4 min · minor
resolved · 28 Sept 2026, 17:07 UTC
This incident has been resolved.
investigating · 28 Sept 2026, 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.
Elevated Flux TTS 1011 Error Rate · 25 Sept 2026, 09:45 UTC · 4 h · minor
resolved · 25 Sept 2026, 13:44 UTC
This issue has been resolved.
investigating · 25 Sept 2026, 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.
Aura-2 TTS Elevated Error Rates for English Voices · 22 Sept 2026, 12:10 UTC · 40 min · major
resolved · 22 Sept 2026, 12:50 UTC
The issue has been resolved.
investigating · 22 Sept 2026, 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.
ISP Backbone Degradation · 2 Sept 2026, 20:22 UTC · 3 h 6 min · minor
resolved · 2 Sept 2026, 23:28 UTC
The upstream ISP failure has been mitigated by rerouting all traffic around that provider.
identified · 2 Sept 2026, 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. https://ecogent.cogentco.com/network-status
[Deepgram EU API] Flux-Multi STT Outage · 25 Aug 2026, 18:01 UTC
resolved · 25 Aug 2026, 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 closures and reconnect loops. A low rate of residual failures continued until 11:30 UTC. This has been fully investigated, mitigated and resolved, service has fully recovered.
Deepgram is listed under Model makers. Status data comes from the official status page and is checked every 5 minutes.All AI service statuses