Live

[Deepgram US API] Intermittent connection timeouts

0

Deepgram reports intermittent connection timeouts and degraded service on its US STT Batch, STT Streaming, TTS Batch, TTS Streaming, and Voice Agent APIs. Deepgram says it is monitoring the issue. Deepgram reports that a network connectivity issue at one US data center disconnected in-progress streaming sessions and caused 503 errors for some new requests.

State

Monitoring

Started

Ongoing for

30 min

Worst impact

Degraded

Timeline

4 updates
17:1817:2517:3317:4017:48
DegradedUpdate postedTimes in UTC

Investigating

12 min 41%

Monitoring

18 min 59%

Updates

Times in UTC

As posted by Deepgram

Monitoring

We are continuing to monitor for any further issues.

Monitoring

A network connectivity issue at one of our US data centers caused in-progress streaming sessions to disconnect, and some new requests received 503 errors while traffic was rerouted to our other data centers. Since then, some customers may have seen intermittent errors and elevated latency while traffic rebalanced across our data centers.

Monitoring

A network connectivity issue at one of our US data centers caused in-progress streaming sessions to disconnect, and some new requests received 429 errors while traffic was rerouted to our other data centers. Since then, some customers may have seen intermittent errors and elevated latency while traffic rebalanced across our data centers.

Investigating

We are currently investigating this issue.

Affected components

10
STT Batch APISTT Streaming APITTS Batch APITTS Streaming APIVoice Agent APIDeepgram Global API (api.deepgram.com) - STT Batch APIDeepgram Global API (api.deepgram.com) - STT Streaming APIDeepgram Global API (api.deepgram.com) - TTS Batch API

Deepgram in the last 90 days

Full history
90 days agoToday

Incidents in 90 days

21

Days with an incident

19

Median duration

59 min

This incident

49% shorter than the median

How long each incident lasted, on the day it started. The outlined bar is this incident.

18 h 59 min
median 59 min
90 days agoToday

Other Deepgram incidents

All incidents

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.

Prompt
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.

RSS
https://outages.live/feed.xml?providers=deepgram
Slack
/feed subscribe https://outages.live/feed.xml?providers=deepgram

FAQ

Go from tracking outages to fixing production issues with Polylane.

Try Polylane