T
Outage recap · Tavus

Tavus outage — October 20, 2025

On October 20, 2025, Tavus had 2 reported incidents on Tavus's official status page. Below is what was reported — impact, timing, and the AI services the same upstream outage could affect.

AWS outage causing Conversation Creation Timeouts

major
Started
Oct 20, 3:30 AM EDT
Resolved
Oct 20, 6:00 AM EDT
Duration
2h 30m

Tavus's updates (1)

  1. resolved · Oct 20, 6:00 AM EDT

    Some conversation creation requests were impacted by the AWS us-east-1 incident and resulted in a 504 Gateway Timeout. This affected CVI. The incident lasted from 10:00 UTC and lasted until 10:20 UTC.

Updates are Tavus's own words from its status page (status: resolved); we never add an inferred cause. The vendor's incident page ↗

Some Conversations Not Joined By Replica due to Ongoing AWS outage

minor
Started
Oct 20, 9:15 AM EDT
Resolved
Oct 20, 10:20 PM EDT
Duration
13h 5m

Tavus's updates (5)

  1. monitoring · Oct 20, 9:15 AM EDT

    AWS outage causing issues one of our infra providers

  2. monitoring · Oct 20, 9:21 AM EDT

    One of our infra providers is affected by the ongoing AWS outage. The previous message incorrectly said a fix had been implemented - we shifted traffic to a different provider.

  3. monitoring · Oct 20, 3:22 PM EDT

    We are continuing to monitor for any further issues.

  4. monitoring · Oct 20, 3:23 PM EDT

    CVI is now operational. We will continue to monitor the issue.

  5. resolved · Oct 20, 10:20 PM EDT

    This incident has been resolved.

Updates are Tavus's own words from its status page (status: resolved); we never add an inferred cause. The vendor's incident page ↗

AIDownCheck is not affiliated with Tavus. This recap summarizes incidents published on Tavus's official status page.