// TOPIC

#latency

14 articles

◆◆◆AdvancedOpenAIDeepgram
01

Voice AI latency budget: hitting sub-500ms in production

A systematic breakdown of every millisecond in the voice AI pipeline and the specific techniques that compound to sub-500ms time-to-first-audio in production.

#voice#latency#production
18 min
◆◆IntermediateLiveKitElevenLabs
02

Voice Agent Frameworks: Vapi vs LiveKit vs Pipecat

Compare Vapi, LiveKit Agents, and Pipecat across latency, cost, telephony, and control — with the exact break-even math to pick the right abstraction.

#voice#latency#architecture
15 min
◆◆IntermediateOpenAIAnthropic
03

Streaming LLM Responses: The Engineering Nobody Talks About

SSE vs WebSockets, partial-JSON parsing for streamed tool calls, backpressure, cancellation, and rendering streamed markdown without flicker — the complete engineering guide.

#streaming#latency#production
20 min
◆◆IntermediateOpenAILiveKit
04

VAD and Turn Detection: The Hardest UX Problem in Voice AI

How voice activity detection and turn-taking work in real-time AI agents — energy vs semantic VAD, barge-in handling, and why getting this wrong is the top user complaint.

#voice#latency#streaming
17 min
◆◆◆AdvancedNVIDIAHugging Face
05

Throughput vs Latency: The GPU Economics of LLM Serving

How tokens/sec, cost per token, TTFT SLAs, and GPU utilization interact — and the engineering decisions that separate a profitable inference deployment from a money pit.

#inference#serving#cost-optimization
16 min
◆◆IntermediateOpenAIGoogle
06

Cascaded pipeline vs native speech-to-speech: when to use each

Chain STT, LLM, and TTS for control — or use one speech-native model for latency. The real tradeoffs, with numbers, and when each architecture wins.

#voice#multimodal#latency
18 min
BeginnerOpenAIDeepgram
07

The Voice Pipeline: STT to LLM to TTS End-to-End

Build the STT to LLM to TTS voice pipeline end-to-end — streaming each stage, budgeting latency, and hitting sub-second time-to-first-audio.

#voice#multimodal#latency
18 min
◆◆Intermediate
08

Speculative decoding: 2-3x latency speedup without changing model quality

How a small draft model proposes tokens the large target verifies in parallel — and why rejection sampling guarantees identical output distributions with real speedup numbers.

#inference#serving#latency
16 min
◆◆IntermediateOpenAIAnthropic
09

Streaming, Batching, and Throughput: Latency vs Cost Trade-offs in Production

How streaming, continuous batching, and async batch APIs interact with latency and cost — and how to configure each without destroying p99 for interactive users.

#inference#serving#cost-optimization
14 min
◆◆IntermediateOpenAIAnthropic
10

Cost, latency, and the model-selection decision tree for reasoning

A practical framework for choosing between reasoning and standard models, with real cost and latency numbers from 2025-2026 deployments.

#reasoning-models#cost-optimization#latency
16 min
◆◆IntermediateOpenAIAnthropic
11

Model routing and cascades: sending the right query to the right model

How to build rule-based routers, intent classifiers, and confidence-based cascades that cut your LLM API bill 60–85% while preserving 95% of frontier quality.

#cost-optimization#latency#production
16 min
BeginnerNVIDIAHugging Face
12

Continuous Batching and Scheduling: Why Static Batching Wastes 70% of Your GPU

How iteration-level scheduling replaced static batching and became the single biggest serving optimization available without any model changes — with real numbers.

#inference#serving#latency
16 min
◆◆IntermediateAnthropicOpenAI
13

Prompt caching deep dive: prefix caching, semantic caching, and when each wins

How provider-side prefix caching and application-side semantic caching work, what they cost, where each breaks, and the decision framework for combining them in production.

#cost-optimization#latency#context-engineering
16 min
Beginner
14

Prefill vs Decode: The Two Phases of Every LLM Request

Why the first token takes longer than every other token, how compute-bound prefill and bandwidth-bound decode shape your entire serving architecture, and what to do about it.

#inference#serving#latency
13 min