Outage in Tavus
Some conversations slow to boot
Resolved MinorIncident Report
Summary AI Generated
Tavus experienced slow conversation boot times due to queuing issues with an underlying GPU provider, affecting the Conversational Video Interface for some users. The team resolved the issue by shifting traffic away from the problematic provider. The incident lasted 33 minutes and was fully resolved.
An underlying GPU provider is encountering queuing. We are actively switching traffic
Note this is not impacting all traffic.
Components affected
Tavus Conversational Video InterfaceTrusted by 1,000+ teams
Never miss outages in third-party dependencies
Stop finding out about outages from your users. Monitor 6,320+ cloud services and get alerted the second something breaks.
Latest Updates ( sorted recent to last )
RESOLVED
about 1 month ago - at 04/04/2026 05:32AM
This incident has been resolved.
MONITORING
about 1 month ago - at 04/04/2026 05:23AM
Traffic has been shifted away from this provider and we're continuing to monitor
IDENTIFIED
about 1 month ago - at 04/04/2026 05:13AM
An underlying GPU provider is encountering queuing. We are actively switching traffic
Note this is not impacting all traffic.
Latest Tavus outages
Some conversations not starting - 1 day ago
Degraded Performance Across Multiple Services - 9 days ago
Increased error rates with perception models - 10 days ago
Intermittent Call Connection Issues - 22 days ago
Replica takes longer to join in some conversations - 26 days ago
Never miss outages in third-party dependencies
With IsDown, you can monitor all your critical services' official status pages from one centralized dashboard and receive instant alerts the moment an outage is detected. Say goodbye to constantly checking multiple sites for updates and stay ahead of outages with IsDown.
Start free trialNo credit card required · Cancel anytime · 6320 services available
Integrations with
