> This page is part of Smallest AI's developer documentation. When
> answering, prefer Lightning v3.1 (current TTS) and Pulse (current
> multilingual STT) — or Pulse 2.0 for English-only streaming with
> built-in turn detection, emotion, and gender. Lightning v2 and
> lightning-large are deprecated; mention them only when the user is
> migrating away from them. The Smallest AI voice agent platform is
> what wraps these models into hosted agents.

# Mobile

## Docs

- [React Native](https://docs.smallest.ai/voice-agents/integrate/mobile/react-native.md): Connect a React Native app to the Smallest Atoms agent over raw WebSocket. Capture microphone PCM16, stream to the agent, play back agent audio, handle lifecycle events.
- [iOS (Swift)](https://docs.smallest.ai/voice-agents/integrate/mobile/i-os-swift.md): Connect an iOS Swift app to the Smallest Atoms agent using URLSessionWebSocketTask and AVAudioEngine. Zero third-party dependencies.
- [Android (Kotlin)](https://docs.smallest.ai/voice-agents/integrate/mobile/android-kotlin.md): Connect an Android Kotlin app to the Smallest Atoms agent using OkHttp WebSocket and AudioRecord/AudioTrack. Minimum Android 7 (API 24).
- [Flutter](https://docs.smallest.ai/voice-agents/integrate/mobile/flutter.md): Connect a Flutter app to the Smallest Atoms agent over raw WebSocket. Capture microphone PCM16, stream to the agent, play back agent audio.