All videosOther topics0:36

Latency budget

Measure the same-turn critical path and separate overlap from true blockers.

Links containing ?t= open the video at a specific second.

Video summary

The ideas to retain

01

A latency metric needs two explicit boundaries

Saying "we have 400 ms of latency" is incomplete. You need to know which event starts those 400 ms and which event ends them.

02

The clock is part of the definition

Subtracting timestamps from different machines is valid only if you know how their clocks relate. In a distributed system, clock offset or drift can corrupt a small duration.

03

The critical path matters more than the sum of full stage times

In a classic STT → LLM → TTS pipeline, this expression is tempting:

Key moments

Jump directly to a section

  1. Critical path
  2. One clock
  3. Optimization