Is Tavus down?

Last checked 1m ago
Current status
Tavus is up

No incidents right now.

Official status page: https://status.tavus.io · Polled every 5 minutes · 21 components tracked

Tavus is operational right now. Last checked 1m ago; the most recent incident resolved 1d ago.

Real-time Tavus status, recent outages, and incident history — pulled directly from Tavus's official status page at https://status.tavus.io every 5 minutes. Pingoru tracks 21 Tavus services and has captured 13 incidents in the last 90 days (99.31% uptime). Get email, Slack, Discord, or webhook alerts the moment Tavus reports a new incident — free for 5 monitors, no credit card.

Users who monitor Tavus also follow these Communications services: GoDaddy Miro Talkdesk GoToConnect SMTP2GO Singlewire Software Slido HelpScout Nuance Flowroute View all 6,000+ providers
Tavus uptime 99.31% uptime · past 90 days
Mon Wed Fri
JunJulAugSep
Less More

Recent outages & incidents

Past 90 days
  1. Resolved 1h 4m
    Started Sep 14, 2026, 05:58 PM UTC · Resolved Sep 14, 2026, 07:02 PM UTC
    Conversational Video Interface
    Timeline · 8 updates
    • investigating · Sep 14, 2026, 05:58 PM UTC

      We are aware of an issue currently impacting tavus conversations, we are investigating.

    • investigating · Sep 14, 2026, 06:03 PM UTC

      It appears this issue is coming from one of our downstream providers, Crusoe. We're continuing to investigate full scope of conversations affected.

    • investigating · Sep 14, 2026, 06:14 PM UTC

      Starting at 17:40 UTC, conversations using our default LLM began experiencing long delays and unresponsive replicas. A GPU provider is returning errors and our automatic failover is recovering most turns, but with significant added latency. We are routing traffic to a backup provider.

    • identified · Sep 14, 2026, 06:18 PM UTC

      This is affecting gemma-4; we recommend our customers switch to a different LLM for immediate needs.

    • identified · Sep 14, 2026, 06:25 PM UTC

      The issue is isolated to our default LLM (gemma-4), served by a GPU provider that began returning errors at 17:40 UTC. As a temporary mitigation we are routing gemma-4 traffic to an alternate model. Customers on gemma-4 may notice a change in response style while this is in effect; we will revert once the provider recovers.

    • identified · Sep 14, 2026, 06:42 PM UTC

      We've confirmed the issue originates with our GPU provider, who has declared a networking incident on their side. We're testing mitigations to route gemma-4 traffic elsewhere. Conversations using other LLMs are unaffected. If you need stability now, you can point your persona at a different LLM.

    • monitoring · Sep 14, 2026, 06:55 PM UTC

      Our upstream GPU provider has applied a mitigation and gemma-4 error rates have returned to normal. We have alternate routing paths staged and ready to enable if the issue recurs. We are monitoring before marking this resolved.

    • resolved · Sep 14, 2026, 07:02 PM UTC

      This incident is now resolved.

    Latest: This incident is now resolved.

  2. Resolved 6m
    Started Sep 04, 2026, 05:29 PM UTC · Resolved Sep 04, 2026, 05:36 PM UTC
    Timeline · 2 updates
    • investigating · Sep 04, 2026, 05:29 PM UTC

      Charlie builder is going through planned maintenance and will be up at 100% capacity within 10 minutes.

    • resolved · Sep 04, 2026, 05:36 PM UTC

      Charlie builder is back working as expected. This issue is resolved.

    Latest: Charlie builder is back working as expected. This issue is resolved.

  3. Resolved 3h 9m
    Started Aug 24, 2026, 01:00 PM UTC · Resolved Aug 24, 2026, 04:09 PM UTC
    Replica Training Service
    Timeline · 3 updates
    • investigating · Aug 24, 2026, 01:00 PM UTC

      We are investigating an elevated error rate in image-to-face trainings.

    • monitoring · Aug 24, 2026, 02:54 PM UTC

      A fix has been rolled out and we are seeing errors resolve. We are continuing to monitor the fix

    • resolved · Aug 24, 2026, 04:09 PM UTC

      This incident has been resolved.

    Latest: This incident has been resolved.

  4. Resolved
    Started Aug 13, 2026, 09:05 AM UTC · Resolved Aug 13, 2026, 08:46 AM UTC
    Timeline · 1 update
    • resolved · Aug 13, 2026, 09:05 AM UTC

      When one of our GPU providers performed maintenance, we asked to migrate traffic to a different cluster beforehand to avoid disruptions. During the migration back, the provider encountered an issue that led to some conversations experiencing an elevated startup time.

    Latest: When one of our GPU providers performed maintenance, we asked to migrate traffic to a different cluster beforehand to avoid disruptions. During the migration back, the provider enc…

  5. Resolved 14m
    Started Aug 05, 2026, 09:41 PM UTC · Resolved Aug 05, 2026, 09:56 PM UTC
    Conversational Video Interface
    Timeline · 4 updates
    • investigating · Aug 05, 2026, 09:41 PM UTC

      We are investigating an issue affecting a small number of conversations configured to use Cartesia for TTS. PAL may intermittently fail to respond during conversations. We are actively investigating the cause.

    • identified · Aug 05, 2026, 09:43 PM UTC

      We are working with Cartesia to restore normal service as quickly as possible. Upstream status: https://status.cartesia.ai/

    • monitoring · Aug 05, 2026, 09:53 PM UTC

      Cartesia has restored service, and conversations using Cartesia TTS are responding normally again. We are actively monitoring the service to ensure continued stability.

    • resolved · Aug 05, 2026, 09:56 PM UTC

      Cartesia has fully restored service, and conversations using Cartesia TTS are responding normally.

    Latest: Cartesia has fully restored service, and conversations using Cartesia TTS are responding normally.

See the full Tavus outage history

8 more incidents in the last 90 days, plus the full multi-year archive of per-service events and update timelines.

Browse Tavus outage history →

Or sign up free to get alerts when Tavus breaks · 10 free monitors · No credit card

Outage history

Past 90 days · 13 incidents View full outage history →