T
Outage recap · Tavus

Tavus outage — August 5, 2026

On August 5, 2026, 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.

Some Custom Replica Creations failing due to upstream Infra Provider Issue

minor
Started
Aug 5, 7:09 AM EDT
Resolved
Aug 5, 8:24 AM EDT
Duration
1h 16m

Tavus's updates (3)

  1. identified · Aug 5, 7:09 AM EDT

    We are experiencing some custom replica training failures due to an upstream infra provider issue. We are working on restarting all new customer replica trainings as soon as possible. Nothing is needed from your side.

  2. monitoring · Aug 5, 7:29 AM EDT

    The upstream provider has recovered and we're relaunching custom replica trainings.

  3. resolved · Aug 5, 8:24 AM EDT

    This incident has been resolved.

What our checks recorded

We checked Tavus 15 times from Tavus's start time to its resolution, once every five minutes. Every one of them reached Tavus's site, so this incident did not show up as a failed page load. Our check loads the public site; it cannot see an API error or a broken feature. Median response time was 236 ms, against 177 ms over the 24 hours before. Tavus posted the incident at Aug 5, 7:09 AM EDT.

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

Intermittent Response Issues with Cartesia TTS

minor
Started
Aug 5, 5:41 PM EDT
Resolved
Aug 5, 5:56 PM EDT
Duration
15 min

Tavus's updates (4)

  1. investigating · Aug 5, 5:41 PM EDT

    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.

  2. identified · Aug 5, 5:43 PM EDT

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

  3. monitoring · Aug 5, 5:53 PM EDT

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

  4. resolved · Aug 5, 5:56 PM EDT

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

What our checks recorded

We checked Tavus 3 times from Tavus's start time to its resolution, once every five minutes. Every one of them reached Tavus's site, so this incident did not show up as a failed page load. Our check loads the public site; it cannot see an API error or a broken feature. Median response time was 232 ms, against 183 ms over the 24 hours before. Tavus posted the incident at Aug 5, 5:41 PM EDT.

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.