← kwindla hultman kramer

Gemini Multimodal Live API + iOS + WebRTC

January 14, 2025

Gemini Multimodal Live API + iOS + WebRTC

"... maybe a beach somewhere, something tropical?"

In this video, Paul walks you through building an iOS voice AI app.

Google recommends WebRTC and the open source Pipecat iOS SDK for building native iOS voice apps with Gemini.

Paul's quick-start shows you how to:
📢 set up a voice client in your iOS app
🛜 specify WebSockets or WebRTC for network transport
📌 attach a delegate to handle lifecycle events (for example "connected", "LLM ready")

Link to Paul's demo repo:

[1]

If you're interested in conversational voice AI, the @pipecat_ai Discord is a great place to hang out.

[2]

  1. https://github.com/pipecat-ai/pipecat-client-ios-gemini-live-websocket-demo
  2. https://discord.gg/pipecat