[Deepgram US API] Connection interruptions
Deepgram reports connection interruptions on the US API. The STT Streaming API and TTS Streaming API on api.deepgram.com were affected. Deepgram reports that the incident is resolved. It lasted about 30 seconds.
State
Resolved
Started
Lasted
1 min
Worst impact
Degraded
Timeline
2 updatesResolved
1 min 100%
Updates
Times in UTCAs posted by Deepgram
We are currently investigating this issue.
Between 16:08:11 and 16:08:24 UTC, new connections to api.deepgram.com could not be established, and some in-progress streaming sessions and requests were disconnected. Clients that retried were able to reconnect immediately. This incident has been resolved.
Affected components
4Deepgram in the last 90 days
Full historyIncidents in 90 days
20
Days with an incident
19
Median duration
1 h 2 min
This incident
99% shorter than the median
Other Deepgram incidents
All incidentsDeepgram·[Deepgram US API] Elevated errors for Aura-2 TTS
Deepgram Aura-2 TTS requests to the TTS Batch API and TTS Streaming API had elevated errors. A portion of requests to /v1/speak failed with HTTP 400. Deepgram reports that the issue is resolved. The outage lasted about 15 minutes.
Deepgram·Flux TTS high latency and websocket disconnects
Deepgram Flux TTS had high latency and websocket disconnects on the TTS API and the Deepgram Public API. Deepgram reported the incident as resolved after 7 minutes.
Deepgram·Flux TTS high latency and websocket disconnects
Flux TTS disconnects occurred between 03:10 - 03:20, with high Flux TTS latency leading up to 03:10. The issue is now resolved.
Deepgram·Elevated errors for Flux streaming STT and Voice Agent sessions
Deepgram Flux streaming speech-to-text requests failed at the US endpoint. Voice Agent sessions with a Flux listen model also failed to start. The incident is resolved and lasted 6 hours and 33 minutes.
Deepgram·Elevated errors from authentication services at one datacenter
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.
Follow Deepgram
Your coding agent knows when Deepgram is down, and tells you when a failure is theirs, not yours. You can also get Deepgram incidents in a feed reader or in Slack.
Install the outages.live MCP server, so that when something breaks you can tell if the cause is a provider we depend on and not my code. It reads the official status pages of cloud, AI, payment and developer providers and gives you their incidents as MCP tools.
Add it as a remote MCP server named "outages" at https://outages.live/mcp (Streamable HTTP, no authentication), with your CLI command or your MCP config file.
Then:
1. Make sure it connects and shows the tools get_provider, list_feed and send_feedback.
2. Call get_provider with "deepgram" and tell me if Deepgram has a problem right now.
3. From now on, when a call to a third-party service fails or becomes slow, call get_provider for that service before you change my code.Paste this into any coding agent. It adds the server with its own MCP setup.
https://outages.live/feed.xml?providers=deepgram/feed subscribe https://outages.live/feed.xml?providers=deepgramFAQ
Go from tracking outages to fixing production issues with Polylane.
Try Polylane