All Systems Operational

Uptime over the past 90 days. View historical uptime.
Conversational Video Interface Operational
90 days ago
99.97 % uptime
Today
API Operational
90 days ago
100.0 % uptime
Today
Replica Training Service Operational
90 days ago
100.0 % uptime
Today
Replica Video Service Operational
90 days ago
99.99 % uptime
Today
Customer Portal Operational
90 days ago
99.99 % uptime
Today
Background Video Service Operational
90 days ago
100.0 % uptime
Today
Bulk Request Service Operational
90 days ago
100.0 % uptime
Today
AWS eks-us-east-1 Operational
AWS ecs-us-east-1 Operational
AWS elb-us-east-1 Operational
AWS lambda-us-east-1 Operational
AWS route53 Operational
AWS sqs-us-east-1 Operational
Google Cloud Platform Google Cloud SQL Operational
Google Cloud Platform Google Cloud Pub/Sub Operational
Google Cloud Platform Google Compute Engine Operational
Google Cloud Platform Google Kubernetes Engine Operational
Google Cloud Platform Identity & Access Management Operational
Slack integration ? Operational
Cartesia ? Operational
90 days ago
100.0 % uptime
Today
Operational
Degraded Performance
Partial Outage
Major Outage
Maintenance
Major outage
Partial outage
No downtime recorded on this day.
No data exists for this day.
had a major outage.
had a partial outage.

No incidents or maintenance related to this downtime.

Nov 14, 2025
Upstream LLM Provider Disruption
Resolved - This incident has been resolved.
Nov 14, 03:00 UTC
Update - The impact was limited, and service performance has since fully recovered.
Nov 14, 03:00 UTC
Identified - We observed a temporary increase in `llm_bad_request` and `llm_internal_server_error` responses stemming from an upstream LLM provider disruption.
Nov 13, 23:00 UTC
Nov 13, 2025
Nov 12, 2025
Increased utterance to utterance latency for tavus-llama
Resolved - This incident has been resolved.
Nov 12, 20:15 UTC
Investigating - We are seeing elevated utterance-to-utterance latency on the tavus-llama llm
Nov 12, 18:45 UTC
Experiencing intermittent log in issues
Resolved - This incident has been resolved.
Nov 12, 19:50 UTC
Monitoring - We have deployed a fix and are monitoring
Nov 12, 19:47 UTC
Identified - We have identified the root cause and are working on the fix.
Nov 12, 19:30 UTC
Conversation Start Failures (GPU Provider Degradation)
Resolved - This incident has been resolved.
Nov 12, 01:05 UTC
Investigating - We’re currently investigating elevated error rates affecting the initialization of a small percentage of conversations with one of our LLM GPU providers.
Nov 11, 21:58 UTC
Nov 11, 2025
Nov 10, 2025

No incidents reported.

Nov 9, 2025

No incidents reported.

Nov 8, 2025

No incidents reported.

Nov 7, 2025

No incidents reported.

Nov 6, 2025

No incidents reported.

Nov 5, 2025
Conversation creation failing
Resolved - This outage was caused by a GPU provider outage, and traffic has now been redirected. All conversations are properly initiating and services are fully restored. Our team will continue to closely monitor.
Nov 5, 03:35 UTC
Investigating - We're currently investigating conversations failing to be created.
Nov 5, 03:25 UTC
Nov 4, 2025

No incidents reported.

Nov 3, 2025

No incidents reported.

Nov 2, 2025

No incidents reported.

Nov 1, 2025

No incidents reported.

Oct 31, 2025

No incidents reported.

← Incident History Powered by Atlassian Statuspage