Skip to content
Tarun Yadav
← All work

Document AI · iOS / Independent product

AudioPage

An iPhone reading and listening app with local speech, document import, and optional AI summaries and document chat.

SwiftUI / Document processing / Local speech / Cloud AI
AudioPage application interface

The engineering challenge

From capability to product.

Importing, reading, listening, and asking questions about a document are different jobs. The core reading experience needs to stay useful even when a cloud feature is unavailable.

Decisions that matter

A dependable local core

Document import, extraction, speech, and playback remain separate from optional cloud intelligence.

Native entry points

Files, the Share Sheet, links, scans, and photos bring content into the app through familiar iPhone workflows.

AI in context

Summaries and document chat sit alongside the material being read, with cloud processing kept distinct from local playback.

What this demonstrates

End-to-end product engineering: connecting model capabilities to usable interfaces, managing processing state and failures, and preparing a release. The platform and workflow here are specific to this product; a business integration would have its own data, permissions, and acceptance checks.

My role: product design, engineering, model integration, and release work. This is an independent product, not a client engagement.

Building a similar workflow? Let’s talk ↗