use case · writing
First drafts at talking speed.
A blank page is easier to talk at than to type at. Explain what you mean the way you'd tell a colleague — the words appear wherever your cursor is, in Word, Google Docs, Notion or a plain text file — then shape them into the real thing.
any editor is a voice editor
There's no special app to write in and nothing to import later. Put the cursor where the words should go, press Ctrl ` , and talk — the text is typed at the cursor and kept on the clipboard as backup. Toggle, push-to-talk, or a hybrid that decides from how long you hold the key: whichever fits the way you work.
There are no word caps and no trial clock, either — a chapter is as welcome as a sentence.
from ramble to readable
Thinking out loud is messy on purpose — that's the thinking part. Say it messy, and let a voice mode tidy the grammar and trim the filler before the text lands; or leave the mode off and get every word exactly as spoken. The polish runs free on the built-in local model or your own Ollama server, and Pro can route it through your own OpenAI or Claude account.
private by default
Journals, half-formed ideas, the paragraph you'd rather nobody read yet: your speech becomes text on your device — audio isn't uploaded to anyone, and the app tracks nothing about you. After the one-time model download it all works with the internet off, on a train or in a café, wherever the writing happens. The full network-use table →
Windows 10/11 today — macOS and Linux builds are on the way. Also see dictating email and writing when typing hurts.