Live / sipgate / Incident
sipgate: Transkribierung erfolgt teilweise sehr langsam
sipgate · sipgate.deMinor incidentResolved2026-10-23 14:43 UTC
Public — what happened
Summary
sipgate said that, starting at 10:04 UTC on 23 October 2026, transcription of calls was running very slowly, which also delayed call summaries and their transfer into connected CRM systems. By 10:51 UTC the company said the delays came from performance problems at Mistral, one of its AI language model partners, and that they affected only customers who had chosen that model in the sipgate app. sipgate suggested a temporary workaround of switching the model setting to OpenAI in the app's AI Assist beta settings, and the incident was not marked resolved.
Affected
sipgate Apps, satellite App
Timeline
- Started — 2026-10-23 10:04 UTC
- Investigating — 2026-10-23 10:04 UTC
- Identified — 2026-10-23 10:51 UTC
- Monitoring — 2026-10-23 13:31 UTC
- Resolved — 2026-10-23 14:43 UTC · 4h 39m after it started
With SquidGrid — where it starts on the route
Independent path health
The status page is the symptom. SquidGrid measures the paths that reach sipgate against their own baselines — whether the routes carrying your traffic degraded, at which handoff, and who owns that stretch.
🔒 Sign in to seeCustomers get the live Provider Assessment Report for sipgate: its full incident track record, what tends to break, and recent public reports of problems.
Included with any paid plan.
Open the sipgate report →
More from sipgate
Covered in The Squid’s Ink, Week 44, 2026, our weekly internet health report.