EnviousWispr

This is a dictation application for macOS that turns speech into polished text at the cursor, inside whatever app is in focus. Audio is transcribed on the Mac itself, stripped of verbal clutter, formatted according to the user's settings and then inserted directly into the target application, with a clipboard fallback when direct insertion is not possible. The vendor lists Slack, Gmail, VS Code, Notion, Obsidian, Linear, Xcode, Terminal and Apple's own apps among the places it works. The pipeline runs in five stages: audio trimming, local transcription, custom vocabulary and formatting, AI polishing, and insertion. Two local speech engines are offered, one tuned for everyday speed across 25 European languages and another covering more than 99 languages. Polishing can run locally or through a cloud provider under the user's own API key, and the vendor states that dictation audio never leaves the Mac and that it never receives dictation text. Features include file transcription for common audio and video formats, a dictionary that learns corrected spellings, saved snippets triggered by a spoken phrase, a live preview while speaking, smart formatting for versions, addresses, dates and slash commands, history that holds an accidentally cancelled recording for 24 hours, and a shortcut to paste the last dictation again. There is no pricing. The application is free and open source, requires no account and carries no subscription, with source published on GitHub. The only cost a user might incur is whatever a chosen cloud provider charges for the optional polishing step. The hardware requirement is strict: macOS 14 or later on Apple silicon, meaning an M1 chip or newer. Intel Macs are not supported.