Service has been fully restored to remaining affected areas. We will share further details on the cause.

After completing the monitoring stage, we have confirmed that STT latency has returned to baseline stability.

The issue has been resolved, everything is back at normal.

We’ll mark this incident as resolved.

Our ticketing system is operational again, though the outage materially affected its setup. We’re working with the team to restore full functionality, but capacity is sufficient to consider the incident resolved.

Latency has since decreased, and we are working on adding more alerts on our side to help us identify and respond to similar latency issues earlier.

The issue has been resolved. A root cause analysis will be shared shortly.

Our engineers have traced media loading error rates as they have returned to baseline. Studio, Audiobooks, Image & Video, Music and Dubbing products should now functional normally.

Inbound calls are currently operational.

The provider resolved the underlying issue at 07:13 UTC and error rates immediately returned to baseline.

After our recent mitigation steps, our engineers have traced SIP call failure rate as it has returned to baseline. We will publish a complete root cause analysis shortly.

The issue has been resolved. All the previous conversations should be visible now.

We've taken steps to mitigate the Speech Engine failures and have confirmed that performance has returned to baseline.

The fix has been released. Outbound WhatsApp messaging is operating normally.

We experienced an increased error rate across multiple services between 17:04 UTC to 17:13 UTC on July 8th in the US region. We are investigating why this happened to prevent recurrence.

We have implemented a fix for the heightened image and video generation error rate. We have not seen any further issues after implementing the fix.

Our engineers were able to push a fix to resolve the failure to save when editing or creating Agent tools that include the Put, Patch, or Post methods in their configuration. We have validated that the tools are now able to be saved, and confirm full resolution.

We have confirmed that dubbing request errors have fully returned to baseline.

The issue has been resolved, the users can now login normally.

We've confirmed that the issue has been resolved with our upstream provider and error rates have remained stable at zero.