Blog
Thoughts on voice input, engineering, and building OnType.
From Spoken Words to Clean Text: How Inverse Text Normalization Works
When you say "three thousand dollars", you expect to see "$3,000" — not the literal words. This is inverse text normalization, and we built a custom engine from scratch to make it work across languages.
Building On-Device Speech Recognition with MLX on Apple Silicon
How we built mlx-swift-asr — an open-source, native Swift library that runs Qwen3-ASR on Apple Silicon at 4–6x real-time speed with zero cloud dependency.
Dictation for Developers: Voice Coding, AI Prompts, and Terminal Input
How developers use voice typing in their daily workflow — from dictating code comments and documentation to composing AI prompts and terminal commands.
Why Your Voice Data Should Never Leave Your Device
Voice is biometric data. Most dictation tools send it to the cloud. We built OnType to process speech entirely on your Mac — here's why that matters.
Voice Typing on macOS: The Complete Guide
Everything you need to know about voice typing on macOS — built-in dictation, third-party tools, setup tips, and how to choose the right approach for your workflow.
OnType 1.0 — Your Voice, Your Keyboard
OnType 1.0 is here. Three ways to turn speech into text — Push-to-Talk for instant dictation, Compose for AI-polished long-form writing, and Translate for seamless bilingual switching. All running locally on your Mac.
Getting Started with OnType
Learn how to set up OnType and start using voice input on your Mac.