Audio & Voice · Free · Pro, one-time $59
Drag in audio or video and get an accurate, speaker-labelled transcript — running OpenAI's Whisper models entirely on your Mac.
All apps
HUUSH
Photo & Video$14.99 · one-time (One-time lifetime license for one active Mac; trial available.)by products.metloub.com
Review and censor profanity in recorded videos on your Mac, with local speech processing and beep, silence or custom sound.
HUUSH is a native Mac app for making clean versions of recorded videos. Smart Clean suggests words in the transcript; check them against the video, adjust timing, choose a beep, silence or custom sound, preview and export MP4, MOV or SRT. Speech recognition and media processing run locally.
Requires Apple silicon and macOS 26+. A trial is available, followed by a $14.99 one-time lifetime license for one active Mac. The current 1.0 installer is unsigned and not notarized. Censor regions affect the full audio mix, including music; unclear and overlapping speech still need manual review. It does not filter live streams.
Download and installer disclosure: https://account.metloub.com/download
More like HUUSH
Productivity · Free · Pro $4.99
Transcribes and translates media, generating captions that can easily be edited by using a video editor-style type of timeline.
Photo & Video · Free · Pro, billed annually; desktop-only license from $29/yr $8.16
An open-source Loom alternative for Mac that records, edits, and shares screen recordings with a link — with a local-first Studio Mode and full self-hosting if you want to own the data.
Photo & Video · $79 · one-time (Standard $89)
A native Mac app for 3D device mockups — drop in a screenshot and get a rotatable, animatable phone, laptop, or desktop render for App Store images, decks, and launch videos.
Developer Tools · Free
A native macOS screen recorder and video editor built with SwiftUI, with smooth zooms, cursor effects, and polished demos.
Productivity · Free · unlimited free plan $0
Converts speech to text and actions on Mac: dictation in any app, file transcription, and voice workflows, with local engines that wo