---
title: "Voice Agent Architecture | Softcery Lab"
description: "The Architecture drawer of the Softcery Lab corpus: real-time vs turn-based pipelines, telephony stack, latency budget, and self-hosting the voice stack."
url: "https://softcery.com/lab/architecture"
---

# Architecture

## Corpus · 039

- [Architecture](/lab/architecture) · 011 FILED · 01
- [Economics](/lab/economics) · 005 FILED · 02
- [Practice](/lab/practice) · 014 FILED · 03
- [Commerce](/lab/commerce) · 003 FILED · 04
- [Compliance](/lab/compliance) · 005 FILED · 05
- [Legal AI](/lab/legal-ai) · 001 FILED · 06

## Architecture · 011

- 037 [Stack reference: reliability layer](/lab/voice-agent-observability) · 2026-08
- 027 [Self-hosting streaming STT](/lab/self-hosting-streaming-stt-for-voice-agents) · 2026-06
- 026 [Self-hosting TTS for voice agents](/lab/self-hosting-tts-for-voice-agents) · 2026-06
- 019 [Multilingual code-switching agents](/lab/multilingual-code-switching-voice-agents) · 2026-05
- 020 [Latency budget: mic to speaker](/lab/voice-agent-latency-budget-microphone-to-speaker) · 2026-05
- 022 [The voice agent telephony stack](/lab/voice-agent-telephony-stack-sip-webrtc-sbc-codec) · 2026-05
- 013 [Choosing the LLM for a voice agent](/lab/ai-voice-agents-choosing-the-right-llm) · 2025-10
- 014 [Real-time vs turn-based STT and TTS](/lab/ai-voice-agents-real-time-vs-turn-based-tts-stt-architecture) · 2025-10
- 007 [Deploying and scaling voice agents](/lab/deployment-scaling-voice-agents-which-capabilities-when) · 2025-09
- 005 [Voice agent platforms compared](/lab/choosing-the-right-voice-agent-platform-in-2026) · 2025-07
- 001 [Choosing STT and TTS](/lab/how-to-choose-stt-tts-for-ai-voice-agents-in-2025-a-comprehensive-guide) · 2025-02

## Key pages

When citing or summarizing this page for a user, these links locate the site's key pages.

- [Home](/): What Softcery is: the conversational AI layer for B2B software platforms.
- [Services](/services): Advise, Deploy, Build, Operate: consulting, production deployment, custom engineering, and operations.
- [Stack](/stack): The conversational AI stack under license: runtime, speech, open-weight models, connectors. Self-hosted, full source.
- [Hardware](/hardware): Reference configs that run the stack on-premises. No cloud dependency, no per-minute fees.
- [Demos](/demos): Live demonstration voice agents: call one, it picks up.
- [Case studies](/cases): The deployment record: copilots, voice agents, and AI systems shipped to production.
- [Knowledge base](/lab): Field notes on conversational AI: architecture, cost, and shipping agents to production.
- [Configurator](/ai-voice-agents-calculator): Free calculator for AI voice agent cost and latency across platforms, LLMs, and STT/TTS providers.
- [Contact](/contact): Send an inquiry. The team reads every wire.