What Do Auto Captions in Mouzz Pro Do?
Mouzz Pro transcribes speech with Apple's on-device speech model and gives you captions in two forms: live captions that appear on screen as you talk, and post-production captions — an editable, word-timed transcript you can style and burn permanently into a new .mp4, or export as a .srt subtitle file.
The transcription runs with word-level timestamps, which is what makes the animated styles possible: Mouzz knows exactly when each word is spoken, so a caption can fill, pop, or slide in perfect sync with your voice — the look viewers know from short-form video, produced on your own machine.
Everything happens locally. Your audio never leaves the Mac, and there is no per-minute metering or monthly plan — captioning is simply part of the Mouzz Pro one-time license. The only download is the first time you use captions, when macOS fetches Apple's speech model for your language; after that, captioning works offline.
Language: there is no language picker. Mouzz transcribes in your Mac's system language, or the closest language Apple's on-device speech model supports, so set your Mac to the language you speak in. Which languages are available is up to Apple, not Mouzz.
How Do Live Captions Work During Presentations and Recordings?
Flip on Live Captions from the menu bar, the Captions page in Settings, or a shortcut you assign, and a caption band transcribes your microphone in real time. It works on its own during presentations and calls, captioning what you say (it listens to your mic, not to other people's audio) — and because it renders on screen, it is captured straight into screen recordings automatically.
The band is tunable: caption size (18 to 60 points), distance from the bottom, how long a caption lingers after you stop talking (Clear After Silence), how it fades, and an optional Smooth Animation. It pairs naturally with the one-take Screen Recorder — arm live captions before a take and the finished video comes out captioned, no post work at all.
Live captions make demos easier to follow for viewers watching without sound, non-native speakers, and anyone in a loud room — the same reasons the major social platforms caption nearly everything.
How Do Burned-In Captions and the Editor Work?
Click Add Captions on the Recording saved toast, use Caption Last Recording, or choose Caption a Video… for any movie file (switch on Auto-Caption After Each Recording to have it start by itself), and Mouzz transcribes the audio into short, word-timed captions. A review window plays the video with the captions overlaid live: fix any word in place, click a timestamp to jump there, then pick a style and export — either a new .mp4 with the captions rendered in permanently, or a .srt sidecar file.
Six styles cover the spectrum: Clean Bar, Bold Outline, and Minimal for classic subtitles, plus three animated styles — Word Fill (color sweeps across each word exactly as it is spoken, as in the visual above), Word Pop (each word bounces as you say it), and Slide Up (words fly in one by one).
Layout is fully controllable: words per caption (2 to 10), one to three lines, text size, an optional background bar, and free horizontal and vertical placement — with a live preview of your text, style, font, size, lines, and position (the word-by-word motion itself shows in the exported video). Fonts: Oswald (the default) and Montserrat ship inside the app, and System, Avenir Condensed, Futura, Impact, and Arial Black are offered when they are installed on your Mac.
Burned-in exports are saved as a new H.264 .mp4 next to the original, named “(Captioned)”. Prefer soft subtitles? Export a standard .srt file (the only subtitle format) and upload it to YouTube, drop it next to the video for VLC, or import it into Premiere Pro or Final Cut Pro.
How Is This Different from Subscription Caption Tools?
Many cloud caption services upload your footage, meter you by the minute, or bill monthly. Mouzz Pro captions on your own hardware: private by construction, works offline once Apple's speech model is downloaded, no usage limits, and included in a one-time $14.99 license alongside the recorder, zoom, and the rest of Mouzz Pro.
For creators publishing to YouTube or short-form platforms, the workflow collapses to: record with Mouzz, fix the odd word, pick Word Fill, export. The result is the same animated-caption look the subscription tools produce — without a render farm in the loop or footage on someone else's server.
Captioning requires macOS 26 or later, which introduced Apple's on-device speech engine with word-level timing. On earlier macOS versions, the rest of Mouzz Pro works normally and the Captions page in Settings shows the requirement.
Frequently Asked Questions
Are auto captions available in the free Mac App Store version?
No. Captions & Subtitles are a Mouzz Pro feature. Pro is the notarized direct-download edition, available with a 7-day free trial and a one-time $14.99 unlock. The free app includes spotlight, ring, trail, click feedback, click sounds, shake-to-locate, and screen annotations.
Is my audio uploaded to a server for transcription?
No. Transcription runs entirely on your Mac using Apple's on-device speech model. Nothing is uploaded and there are no usage limits or per-minute fees. The first time, macOS downloads the speech model for your language; after that, captioning works offline.
Can I edit the transcript before burning captions in?
Yes. The review window shows every caption with word-level timing — edit any word in place, click a timestamp to play from that moment, and nudge start and end times. Your corrections carry into both the burned-in export and the .srt file.
Which caption styles are included?
Clean Bar, Bold Outline, and Minimal for classic subtitles, plus three animated styles synced to word timestamps: Word Fill (color fills each word as it is spoken), Word Pop, and Slide Up. Font, words per caption, size, lines, background, and position are all adjustable, with a live preview (the word-by-word motion appears in the exported video).
What are the system requirements for captions?
Captions require macOS 26 or later, which provides Apple's on-device speech recognition with word-level timestamps. The rest of Mouzz Pro runs on macOS 13.0 and up.
Which languages can Mouzz caption?
Mouzz uses your Mac's system language, matched to the closest language Apple's on-device speech model supports. There is no language picker in the app, and the list of supported languages comes from Apple, so set your Mac's language to the one you speak in before captioning.
Can I caption videos that were not recorded with Mouzz?
Yes. 'Caption a Video…' opens any movie file, such as .mp4 or .mov — Mouzz transcribes its first audio track, you edit the transcript, and you export a burned-in .mp4 or a .srt subtitle file, exactly as with Mouzz recordings.
Explore More Mouzz Features
Captions & Subtitles ship in Mouzz Pro, available now — download it at mouzz.dev/pro/download with a 7-day free trial, then a one-time $14.99 unlock. The free Mouzz app on the Mac App Store gives you spotlight, ring, trails, click effects, and screen annotations.
Get Mouzz Pro — Free 7-Day Trial