Skip to content
Tarun Yadav
← All work

Speech AI · macOS / Independent product

EchoText

Private Mac dictation with local speech recognition, a global shortcut, and text insertion across applications.

Visit the product ↗SwiftUI / Core ML / Local transcription / System integration
EchoText application interface

The engineering challenge

From capability to product.

Recognition quality is just one part of dictation. Capturing audio, permissions, shortcuts, and inserting text reliably determine whether people can use it in their daily work.

Decisions that matter

Stay in the workflow

A global shortcut brings speech recognition to the application the user is already working in.

Recover gracefully

Clipboard fallback provides a recovery path when direct text insertion is unavailable.

Keep control local

On-device recognition and local history controls make data handling part of the experience.

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 ↗