|
|
|
|
Ask HN: How do you keep voice AI latency low while load spikes?
|
|
1 points
by didro
347 days ago
|
|
|
Hey guys, I'm doing a research and have a question. What do you do when traffic to voice AI agents spikes? As far as I know, native autoscaler of Kubernetes (HPA) doesn't catch up quite often with that - resulting into a prohibitively high latency. Would be glad to know your experience if you don't mind. Thanks! |
|
|