Project 01 / macOS App

EchoText

Problem: Developers and writers waste time typing. Existing dictation tools require internet or subscriptions.

Solution: Built 100% on-device dictation for macOS using WhisperKit and Metal acceleration. Works offline, instant insertion in any app, 99+ languages.

View on Gumroad ↗Case Study

Tech Stack

SwiftUI

WhisperKit ML

macOS APIs

Apple Neural Engine

Impact

Sold on Gumroad

3.7x faster than typing

Role

Solo founder & developer

(0→1)

Platform

macOS Native

Built with SwiftUI for seamless macOS integration and native performance.

ML Engine

WhisperKit

On-device ML using WhisperKit with Metal acceleration for real-time transcription.

Processing

Apple Neural Engine

Leverages Apple Silicon Neural Engine for ultra-fast local inference.

Distribution

Gumroad

Direct distribution to macOS users with instant download and activation.

Interface Preview / 01

1 / 10

Live Interactive Demo →

echotext_v1.0_process.log

[00:04] SPK_1:Welcome to the technical review for the project.
[00:08] SPK_2:Thanks. Can we discuss the latency on the transcription pipeline?
[00:12] SPK_1:Currently we are seeing sub-300ms response times globally.
_ system ready... |