Experiencing High Latency
On the VAPI dashboard, our latency is supposed to be ~1100ms - but on the actual calls it ranges between ~3500ms and ~4000ms. Our Assistant's prompt structure is pretty simple and well structured. We also tried running it with a super simple prompt to see if the issue was on the prompting side, and still got the same delay.
Here is some examples from our call logs:
Turn Latency: 3745ms (Endpointing 1501ms, Model 1351ms, Voice: 887ms)
Turn Latency: 3736ms (Endpointing 1502ms, Model 1287ms, Voice: 924ms)
Our calls are made from Europe. We're available to invest in a solid server infrastructure if needed.
Currently our only goal is to lower the latency at least <2000ms as the current latency is a disaster with the calls.
Thanks for the help.
Here is some examples from our call logs:
Turn Latency: 3745ms (Endpointing 1501ms, Model 1351ms, Voice: 887ms)
Turn Latency: 3736ms (Endpointing 1502ms, Model 1287ms, Voice: 924ms)
Our calls are made from Europe. We're available to invest in a solid server infrastructure if needed.
Currently our only goal is to lower the latency at least <2000ms as the current latency is a disaster with the calls.
Thanks for the help.
