Glossary
Latency
Latency is the delay between sending a request to an AI service and getting the answer back.
What it means in practice
It matters for phone and live-chat assistants, where long pauses feel broken. Larger models and longer answers are usually slower.
Example
A voice assistant that takes several seconds to answer feels awkward on a phone call.
Guide: A phone assistant for your top 10 questions, labelled as AITerm: InferenceAll terms