About

I’m building a simple iOS prototype for a sleep product. I need an engineer who can create a lightweight app in Xcode that listens to voice commands, converts speech to text, plays specific audio files I upload, and responds using natural text-to-speech. You should be comfortable with Swift, AVAudio playback, integrating APIs like OpenAI Realtime or ElevenLabs STT/TTS, and wiring basic agent logic to trigger actions such as “play track,” “save note,” or “start morning brief.” This is a focused prototype, not a full app. I only need a functional demo that runs on-device and shows the core conversation loop. You must know Swift, SwiftUI or UIKit, audio sessions, background audio, and simple API calls. Bonus if you’ve worked with speech frameworks or Spotify/Apple Music integration. I’m looking for a clean, reliable build that I can test directly on an iPhone.