ArchestackGitHub ↗ (opens in a new tab)

#66th of 16 in Voice and realtime

agent-starter-swift

SwiftUI voice agent client for iOS, macOS and visionOS on LiveKit

Documentation ↗ (opens in a new tab)Repository on GitHub ↗ (opens in a new tab)
Stars
96
License
MIT
Last commit
Sep 2026
Language
Swift

Overview

Xcode project on the LiveKit Swift SDK with voice, text, camera and screen-share input, transcriptions and avatar rendering, built on the SDK's Session and LocalMedia observables with preconnect audio buffering on by default. Targets iOS, iPadOS, macOS and visionOS. Set AgentToConnect.current to a development token server id for your own agent, then swap in an EndpointTokenSource for production.

Who it is for: Apple-platform developers adding a LiveKit voice agent

Strengths

  • Voice, text, video and screen-share input toggled per feature in code
  • Preconnect audio buffer makes connects feel instant
  • Renders the agent's avatar video automatically when published
  • One codebase for iOS, iPadOS, macOS and visionOS

Weaknesses

  • Video and screen share need a physical device, not the Simulator
  • Production token generation is left to you
  • No tests
  • App Store archive warns about missing LiveKitWebRTC dSYMs

What it needs

  • Swift
  • Needs LiveKit Cloud project, a LiveKit agent, token server
  • GitHub template

Also in Voice and realtime

See all 16
Also in Voice and realtime
RankProjectScore
1agent-starter-reactNext.js voice assistant frontend for LiveKit Agents947 stars, MIT51 out of 100
2agent-starter-pythonPython voice agent on LiveKit Agents with turn detection and simulations264 stars, MIT50 out of 100
3agent-starter-nodeNode.js voice agent on LiveKit Agents with turn detection and simulations114 stars, MIT50 out of 100
#4voice-ui-kitReact components and templates for Pipecat voice agent frontends419 stars, BSD-2-Clause45 out of 100
#5pipecat-examplesRunnable Pipecat voice agent examples for phone, web and deployment395 stars, BSD-2-Clause41 out of 100