Back

Deepgram Status

Operational

Last incident: 5/14/2026

Current Status
Overall StatusOperational
Last IncidentElevated 5XX Errors for Non-English Batch STT Requests with Redaction
Incident Statusresolved

Recent Incidents

Elevated 5XX Errors for Non-English Batch STT Requests with Redaction
5/14/2026, 7:00:54 PM

May 14, 19:00 UTC
Resolved - This issue has been resolved.

May 14, 18:52 UTC
Investigating - We are currently investigating an increase in 5XX errors for non-English STT requests that are using redaction.

Intermittent 404 HTTP errors Batch STT English
5/12/2026, 6:07:11 PM

May 12, 18:07 UTC
Resolved - This incident has been resolved.

May 12, 16:18 UTC
Investigating - 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.

Voice Agent third-party provider instability (ChatGPT 4o)
5/12/2026, 4:55:16 PM

May 12, 16:55 UTC
Resolved - This incident has been resolved.

May 11, 16:35 UTC
Identified - 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.

Voice Agent third-party provider instability (Claude Sonnet 4.5)
5/1/2026, 6:22:20 PM

May 1, 18:22 UTC
Resolved - This incident has been resolved.

Apr 24, 05:45 UTC
Investigating - 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.

Voice Agent third-party provider instability (Google Gemini LLMs)
5/1/2026, 6:21:42 PM

May 1, 18:21 UTC
Resolved - This incident has been resolved.

Apr 21, 15:59 UTC
Identified - 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.

Frequently Asked Questions