The full stack behind a Gemini 3.8 Live iOS app: audio, transcription and camera components
amos_gyamfi · x · 2026-09-16
A follow-up breakdown of the iOS real-time AI app tutorial: Gemini 3.8 Live (and Extended Thinking) for realtime audio generation, Gemini 3.5 Transcribe for transcription, SwiftUI AI Components for the transcription UI, and Stream Video for SwiftUI for the live camera feed—built with coding models using Stream Swift and CLI Skills.
Related event: Developer Recreates Gemini Live-Style Realtime Voice iOS App(2 posts)→
More from coding & agent
- Astra's Context Compaction Takes 3x Longer Than Sol, Dev Notes — banteg · 2026-09-16
- Simfinity.js example: expose selected GraphQL operations as MCP tools via stdio — Affectionate_Hawk971 · 2026-09-16
- GPT-6 spent $367 and 6.1M tokens over 7h50m to build a rocket in The Universim on its own — Angaisb_ · 2026-09-16
- DataFast Adds MCP/API Support for Mention Tracking and Chart Notes — marclou · 2026-09-16
- Semantica Hits 13k Stars: Open-Source Graph-Native Infrastructure for Accountable AI — tom_doerr · 2026-09-16
- Dev says his session-less personal assistant with continuous memory has users hooked for months — matteoianni · 2026-09-16