Tavus Outage History

Tavus is up right now

There were 13 Tavus outages since February 12, 2026 totaling 15h 50m of downtime. Each is summarised below — incident details, duration, and resolution information.

Source: https://status.tavus.io

Minor April 30, 2026

Degraded Performance Across Multiple Services

Detected by Pingoru
Apr 30, 2026, 04:43 PM UTC
Resolved
Apr 30, 2026, 08:43 PM UTC
Duration
4h
Affected: Conversational Video Interface
Timeline · 4 updates
  1. investigating Apr 30, 2026, 03:29 PM UTC

    We’re currently seeing elevated error rates across multiple parts of our stack, including perception, knowledge base, Gemini conversation LLM, objectives, and guardrails.

  2. identified Apr 30, 2026, 04:43 PM UTC

    We’ve identified the root cause of the issue and are working on deploying a fix. Update: All services, except perception, are currently operating as expected.

  3. monitoring Apr 30, 2026, 06:31 PM UTC

    All deployments have been restored, and the issue with our cloud provider has been resolved. Services are now up and running, and we’re continuing to monitor to ensure stability.

  4. resolved Apr 30, 2026, 08:43 PM UTC

    This incident has been resolved.

Read the full incident report →

Minor April 29, 2026

Increased error rates with perception models

Detected by Pingoru
Apr 29, 2026, 03:21 PM UTC
Resolved
Apr 29, 2026, 08:29 PM UTC
Duration
5h 8m
Affected: Conversational Video Interface
Timeline · 4 updates
  1. investigating Apr 29, 2026, 03:21 PM UTC

    We are investigating increased error rates with Raven-0 and Raven-1

  2. identified Apr 29, 2026, 07:29 PM UTC

    The issue was identified and a fix has been deployed

  3. monitoring Apr 29, 2026, 07:31 PM UTC

    Raven-0 and Raven-1 are now operating normally, and we are actively monitoring the system to ensure continued stability.

  4. resolved Apr 29, 2026, 08:29 PM UTC

    The incident has been resolved, and Raven is now working as expected.

Read the full incident report →

Notice April 17, 2026

Intermittent Call Connection Issues

Detected by Pingoru
Apr 17, 2026, 04:05 PM UTC
Resolved
Apr 17, 2026, 07:50 PM UTC
Duration
3h 45m
Affected: Conversational Video InterfaceAPI
Timeline · 2 updates
  1. monitoring Apr 17, 2026, 04:05 PM UTC

    There are intermittent call connection issues tied to upstream Daily and Cloudflare outages. Daily: https://status.daily.co/ Cloudflare: https://www.cloudflarestatus.com/

  2. resolved Apr 17, 2026, 07:50 PM UTC

    Cloudflare has implemented a fix and downstream services are returning to normal service

Read the full incident report →

Major April 10, 2026

Elevated Error Rate When Joining Conversations

Detected by Pingoru
Apr 10, 2026, 03:42 PM UTC
Resolved
Apr 10, 2026, 03:57 PM UTC
Duration
14m
Affected: Conversational Video Interface
Timeline · 3 updates
  1. identified Apr 10, 2026, 03:42 PM UTC

    We are seeing elevated API errors from our webRTC provider Daily https://status.daily.co/incidents/0vkhkxd7m20b

  2. monitoring Apr 10, 2026, 03:48 PM UTC

    A fix has been released by the Daily team, we are seeing traffic return to normal and will be continuing to monitor

  3. resolved Apr 10, 2026, 03:57 PM UTC

    This incident has been resolved

Read the full incident report →

Minor April 5, 2026

Conversations not properly initiating

Detected by Pingoru
Apr 05, 2026, 10:49 PM UTC
Resolved
Apr 05, 2026, 10:56 PM UTC
Duration
7m
Affected: Conversational Video Interface
Timeline · 3 updates
  1. investigating Apr 05, 2026, 10:36 PM UTC

    Conversations requests are succeeding, but encountering issues at the GPU level which are causing replicas to not properly join

  2. monitoring Apr 05, 2026, 10:55 PM UTC

    A sub GPU provider has encountered a 10 minute outage involving their AWS instance. Traffic was automatically rerouted, although some conversations which were already sent to this provider did not properly join. All traffic is now performing within SLA, and we're continuing to monitor.

  3. resolved Apr 05, 2026, 10:56 PM UTC

    This incident has been resolved.

Read the full incident report →

Minor April 4, 2026

Some conversations slow to boot

Detected by Pingoru
Apr 04, 2026, 05:03 AM UTC
Resolved
Apr 04, 2026, 05:32 AM UTC
Duration
29m
Affected: Conversational Video Interface
Timeline · 3 updates
  1. identified Apr 04, 2026, 05:13 AM UTC

    An underlying GPU provider is encountering queuing. We are actively switching traffic Note this is not impacting all traffic.

  2. monitoring Apr 04, 2026, 05:23 AM UTC

    Traffic has been shifted away from this provider and we're continuing to monitor

  3. resolved Apr 04, 2026, 05:32 AM UTC

    This incident has been resolved.

Read the full incident report →

Critical March 26, 2026

Some conversations not initiating

Detected by Pingoru
Mar 26, 2026, 09:22 PM UTC
Resolved
Mar 26, 2026, 09:55 PM UTC
Duration
32m
Affected: Conversational Video Interface
Timeline · 5 updates
  1. investigating Mar 26, 2026, 09:30 PM UTC

    We are currently investigating

  2. monitoring Mar 26, 2026, 09:40 PM UTC

    We’ve identified the root cause of the issue and are actively monitoring the conversations.

  3. monitoring Mar 26, 2026, 09:40 PM UTC

    We are continuing to monitor for any further issues.

  4. monitoring Mar 26, 2026, 09:42 PM UTC

    Conversations are now starting normally. Some conversations may still experience higher-than-usual startup times. We’re continuing to monitor the situation closely.

  5. resolved Mar 26, 2026, 09:55 PM UTC

    We experienced a brief disruption due to a configuration change that impacted conversation routing, causing some conversations to stall or take longer to start. The issue has been resolved and all systems are now operating normally.

Read the full incident report →

Minor March 25, 2026

Some conversations are encountering increased startup times

Detected by Pingoru
Mar 25, 2026, 01:24 PM UTC
Resolved
Mar 25, 2026, 01:39 PM UTC
Duration
14m
Affected: Conversational Video Interface
Timeline · 3 updates
  1. identified Mar 25, 2026, 01:24 PM UTC

    The issue has been identified and a fix is being implemented.

  2. monitoring Mar 25, 2026, 01:37 PM UTC

    We have rerouted traffic to healthy providers. Traffic has returned to normal.

  3. resolved Mar 25, 2026, 01:39 PM UTC

    This incident has been resolved.

Read the full incident report →

Minor March 10, 2026

Some conversations took longer time start

Detected by Pingoru
Mar 10, 2026, 08:20 PM UTC
Resolved
Mar 10, 2026, 08:20 PM UTC
Duration
—
Timeline · 1 update
  1. resolved Mar 10, 2026, 08:20 PM UTC

    We detected several conversations with start times exceeding 10 seconds. We have diverted traffic and are continuing to monitor the situation.

Read the full incident report →

Notice March 6, 2026

Some conversations not starting up

Detected by Pingoru
Mar 06, 2026, 01:45 PM UTC
Resolved
Mar 06, 2026, 01:27 PM UTC
Duration
—
Timeline · 1 update
  1. resolved Mar 06, 2026, 01:45 PM UTC

    We have identified an issue with one of our GPU providers and shifted traffic away from them

Read the full incident report →

Major February 17, 2026

List Replicas Endpoint

Detected by Pingoru
Feb 17, 2026, 02:06 AM UTC
Resolved
Feb 17, 2026, 02:23 AM UTC
Duration
17m
Affected: API
Timeline · 2 updates
  1. investigating Feb 17, 2026, 02:06 AM UTC

    We are currently investigating an issue with our List Replicas endpoint

  2. resolved Feb 17, 2026, 02:23 AM UTC

    API is back to operational

Read the full incident report →

Minor February 12, 2026

Conversations slow to join

Detected by Pingoru
Feb 12, 2026, 07:45 PM UTC
Resolved
Feb 12, 2026, 08:10 PM UTC
Duration
24m
Affected: Conversational Video Interface
Timeline · 3 updates
  1. investigating Feb 12, 2026, 07:45 PM UTC

    Some conversations might be slow to join. We're actively investigating

  2. monitoring Feb 12, 2026, 07:54 PM UTC

    Traffic has been automatically shifted away from the faulty provider and service seems to be fully restored.

  3. resolved Feb 12, 2026, 08:16 PM UTC

    This incident has been resolved.

Read the full incident report →

Looking to track Tavus downtime and outages?

Pingoru polls Tavus's status page every 5 minutes and alerts you the moment it reports an issue — before your customers do.

  • Real-time alerts when Tavus reports an incident
  • Email, Slack, Discord, Microsoft Teams, and webhook notifications
  • Track Tavus alongside 5,000+ providers in one dashboard
  • Component-level filtering
  • Notification groups + maintenance calendar
Start monitoring Tavus for free

5 free monitors · No credit card required