Partial Degraded CVI Experience Stemming from ElevenLabs Incidents
minor- Started
- Nov 18, 11:04 AM EST
- Resolved
- Nov 18, 4:03 PM EST
- Duration
- 4h 59m
Tavus's updates (4)
- investigating · Nov 18, 11:04 AM EST
ElevenLabs has posted on their status page that increased latency and API errors on their end is causing degraded performance for agent conversations.
- investigating · Nov 18, 12:33 PM EST
Confirming that the ElevenLabs outage is affecting parts of the Video to Replica training pipeline.
- monitoring · Nov 18, 3:33 PM EST
ElevenLabs has reported that their latency is back to normal levels and they are seeing a reduction in error rates across all products. They are still monitoring to confirm resolution as are we.
- resolved · Nov 18, 4:03 PM EST
ElevenLabs has posted that their systems are now operational across all products, we are now marking this as resolved.
What our checks recorded
We checked Tavus 60 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 238 ms, against 275 ms over the 24 hours before. Tavus posted the incident at Nov 18, 11:04 AM EST.
Updates are Tavus's own words from its status page (status: resolved); we never add an inferred cause. The vendor's incident page ↗