We have identified the problem and put in a correction. Service should be behaving as usual. The cache was in a bad state and some speech audio generations would have been corrupted. This issue began with a deployment on our side at 3am PST. So any videos between then and 1130am PST might have been impacted
Resolved
We have identified the problem and put in a correction. Service should be behaving as usual. The cache was in a bad state and some speech audio generations would have been corrupted. This issue began with a deployment on our side at 3am PST. So any videos between then and 1130am PST might have been impacted
Investigating
We had a voice cache degradation where some generations were not executed and multi-scene videos would have been impacted. The issue began around 3am PST