Verbaform
Your voice is the input and the editor
What it does
Verbaform is programmable dictation for macOS: your voice is both the input and the editor. Speak exact commands to trim fillers, redact names, structure text, chain edits, and create reusable macros. Core recognition and deterministic edits run locally on Apple silicon, preserve every spoken word, and work in every text field. The complete local product is free; optional Pro adds managed cloud transcription and scoped AI actions.
Edit your dictation by voice with deterministic commands. Verbaform runs locally on Apple silicon, preserves every spoken word, and works in every Mac text field.
Speak commands that edit what you already said. Deterministic, local, and every word you spoke kept verbatim. Capture your natural train of thought, then shape it without reaching for the keyboard. Speak exact edits, scopes, variables, templates, and macros. The same command does the same thing. Recognition and deterministic edits stay local. Network features are explicit and scoped. Most dictation software guesses what polished should mean. Verbaform keeps every word, then changes only what you tell it to change. Every word lands verbatim. Nothing is rewritten behind your back. The launch email should say that nothing you dictate is ever lost. 2 edits The exact edit, in milliseconds, on…from tryverbaform.com
Does the same job
all alternatives →
More work this month
the category →
The app store for voice native apps that lives in your notch
Work · 28d ago · voiceos.com
The New Calendly▲211Handle all of the work before, during, and after meetings
Work · 17d ago · calendly.com
Launched alongside, August 2026
the whole month →- TL
Life & fun · 10d ago · louisabraham.github.io
- SA
Hello HN! I found that picking out plausible but diverse skin tones for my digital art and game development projects was kind of difficult, and I got curious about if there was a way to define a color space that made it easy. I've built a color picker and procedural generation algorithm based on the space as well as a bunch of other fun js features and demos throughout the page that use the equations. If you find it interesting, I have lots of explanations of how I built it and what properties the space has. The methodology might be a bit shaky, but hopefully the result is as helpful for…
Life & fun · Aug 2026 · toneyalexander.github.io
I trained a 125M-parameter transformer to autocomplete piano performances in real time (~108 notes/sec on an iPhone 15). The idea is basically GitHub Copilot or Tabnine, except instead of prompting it with code, you prompt it by playing a few notes on a MIDI piano. The model then continues what you played, entirely on-device. The app is free if anyone wants to try it. Happy to answer questions about the model, training, Core ML, or the many things that didn't work.
AI · 16d ago · simedw.com