Tavus logo

Is Tavus Down?

AI & Machine LearningLive status, outages, and incident history

No. Tavus is up right now.

Every monitored Tavus system is operational as of October 11, 2026. PulsAPI did not find an outage in its latest check of the official status feed.

OperationalChecked just nowLive · 60s while moving

Know the moment Tavus breaks

Tavus is healthy right now. We keep checking (every 60 seconds once it starts moving) and email you the moment that changes.

Free, no password, no card. Unsubscribe in one click.

How we know: the official Tavus status page, PulsAPI's own check (every 60 seconds while one is moving, every 5 to 20 minutes while it is stable), and outage reports from engineers. How PulsAPI monitoring works

Tavus Component Status

The main Tavus systems on this page. All 21 are operational right now.

21operational
API
Operational
AWS ecs-us-east-1
Operational
AWS eks-us-east-1
Operational

18 more components tracked

Their status is in the bar above. Free accounts see every component by name.

Also tracking AWS elb-us-east-1, AWS lambda-us-east-1, AWS route53, AWS sqs-us-east-1, Background Video Service, Bulk Request Service, Cartesia, Conversational Video Interface, Customer Portal, Google Cloud Platform Google Cloud Pub/Sub, Google Cloud Platform Google Cloud SQL, Google Cloud Platform Google Compute Engine, and 6 more.

See all of them free

Component statuses may change independently during partial outages.

Recent Tavus Outages & Incidents

Incident history from the official Tavus status page, including resolution updates.

Image Face Training DegradedResolved Sep 23, 2026 · 3h 48mResolved

This incident has been resolved. --- [2026-09-23T16:24:00.346Z] (monitoring) Error rates are returning to baseline and we are continuing to monitor the pipeline --- [2026-09-23T16:05:28.881Z] (investigating) We are investigating increased error rates when training a Face with an image.

Conversations using Gemma-4 are experiencing delaysResolved Sep 14, 2026 · 1h 4mResolved

This incident is now resolved. --- [2026-09-14T18:58:58.550Z] (monitoring) 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. --- [2026-09-14T18:42:43.844Z] (identified) 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. --- [2026-09-14T18:25:22.056Z] (identified) 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. --- [2026-09-14T18:18:12.650Z] (identified) This is affecting gemma-4; we recommend our customers switch to a different LLM for immediate needs. --- [2026-09-14T18:14:02.562Z] (investigating) 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. --- [2026-09-14T18:03:21.819Z] (investigating) It appears this issue is coming from one of our downstream providers, Crusoe. We're continuing to investigate full scope of conversations affected. --- [2026-09-14T17:58:09.128Z] (investigating) We are aware of an issue currently impacting tavus conversations, we are investigating.

Charlie Builder Maintenance for 10 MinutesResolved Sep 4, 2026 · 6 minResolved

Charlie builder is back working as expected. This issue is resolved. --- [2026-09-04T17:29:55.338Z] (investigating) Charlie builder is going through planned maintenance and will be up at 100% capacity within 10 minutes.

Tavus Uptime History

Daily uptime recorded by PulsAPI over the last 90 days, with the days that carried a Tavus incident marked. Each day is measured from our own checks, so the record continues even when the vendor publishes nothing.

Uptime history91 days observed
Jul 13100.00% average · 10 days with incidentsOct 11

Going further back: Tavus uptime by month and every recorded Tavus outage.

Live Tavus Outage Reports

Problems reported by engineers using Tavus. Reports often appear 10 to 20 minutes before the official status page moves, and stay on this page for 90 days.

Reports, last 24 hours0 total
24h agoNothing reportednow

No Tavus problems reported yet.

Something wrong with Tavus on your end?

Reports are anonymous, take about ten seconds, and help the next engineer who checks.

About Tavus

Tavus is a personalized AI video platform enabling automated personalized video generation at scale for sales and marketing. Track Tavus status and outages here.

Over the past 30 days, PulsAPI has measured Tavus uptime at 99.99%. Response times, incident history, and SLA tracking for Tavus are available on the PulsAPI dashboard.

Tavus Status FAQ

Is Tavus down right now?

The verdict at the top of this page comes from the latest poll of the official Tavus status feed and refreshes automatically, so you are not looking at a stale cached answer. PulsAPI re-checks a vendor every 60 seconds whenever it is not fully operational, or has changed status in the last 30 minutes, so an incident is always on the fastest cadence. Vendors that are stable and rarely watched are re-checked every 5 to 20 minutes instead.

What should I do if Tavus is not working?

Check the component list on this page first to see if your failure matches a known outage. If it does, you can report the issue for other engineers, follow the incident timeline for vendor updates, and run any fallback your app supports until Tavus recovers.

How do I check Tavus uptime history?

PulsAPI tracks Tavus uptime over 30, 60, and 90-day rolling windows. The current 30-day uptime is 99.99%. The 90-day uptime strip on this page is public: no account needed. A free account adds alerts whenever Tavus changes state, plus 15 days of incident detail; Pro extends that to 90 days and Business to 13 months.

How fast does PulsAPI detect Tavus outages?

PulsAPI reads the official Tavus status page. PulsAPI re-checks a vendor every 60 seconds whenever it is not fully operational, or has changed status in the last 30 minutes, so an incident is always on the fastest cadence. Vendors that are stable and rarely watched are re-checked every 5 to 20 minutes instead. Alerts reach Slack, Discord, Microsoft Teams, PagerDuty, or email within seconds of detection.

Does PulsAPI track individual Tavus components?

Yes. PulsAPI monitors 21 individual Tavus components, so you can see which service or region is affected instead of a generic "service degraded" banner.

Can I get alerts when Tavus goes down?

Yes. Create a free account and subscribe to Tavus: the free plan covers three services with unlimited email alerts and no monthly notification cap. Paid plans lift the monitor limit entirely (Pro and above do not meter how many vendors you watch) and route the same alerts into Slack, Discord, Microsoft Teams, PagerDuty and webhooks.

How do I report an issue with Tavus to the community?

Click "Report an issue" at the top of this page, pick the issue type and severity, and optionally add your region and a short note. Reports are anonymous and help other engineers spot Tavus problems early. Official status pages often lag real incidents by 10 to 20 minutes.

Is there a free way to monitor Tavus?

Yes. The free plan covers 3 monitored services with unlimited email alerts, permanently, so Tavus plus two more costs nothing. Every new account also opens with a 30-day Business trial (unlimited monitors, Slack alerts, SLA reporting) with no credit card.

Track Tavus with the rest of your stack

2463+ vendors in one dashboard, and an email the moment any of them changes state. Three free, and no monitor limit at all from $29/mo, unlike the alternatives, which keep charging by the monitor.

Start free, 3 services