How to transcribe video to text on a Mac, and what macOS can do by itself
By Ryleigh Newman ยท Published
You can transcribe video to text on a Mac three ways. Live Captions, built into macOS, captions a video's speech in real time while it plays. Final Cut Pro, Apple's paid video editor, turns the speech in a clip into timed captions, in U.S. English only. YapToText, the free app I built, transcribes the video file itself on your Mac and gives you plain text.
The right one depends on what you want back: captions to follow along, a caption file with timings, or words to paste into a document. My hands make typing difficult, so I built YapToText to turn speech into text without a keyboard, and a video's soundtrack is just more speech. It needs macOS 14 or later on Apple silicon, and files have no minute cap.
Download for free. No account, nothing locked, macOS 14 or later on Apple silicon. Source on GitHub.
On this page: 9 sections
Steps
- Open YapToText and go to the Utility page.
- In the Transcribe a file card's mode menu, pick Raw Transcription for the words as spoken, or a mode such as Note.
- Drop the video file on the card, or click Choose File and pick it.
- Wait for the text to appear in the card.
- Click Copy, or Insert to type the text into the app you were using before.
Follow a video with Live Captions
Live Captions is Apple's built-in, real-time transcription. Apple says audio is processed on device, and by default it captions audio from all apps, so a video playing anywhere on your Mac gets captions. Live Captions helps you follow a video as it plays, and Apple's guide describes no way to keep the words.
Step 1: Turn it on
- You: Choose Apple menu, System Settings, click Accessibility, then Live Captions, and turn it on.
- macOS: Shows the Live Captions window. The first time, it downloads language data, so you need to be online once.
- Check: The window appears. Apple says it hides when no audio is detected; choose Keep Onscreen from the Live Captions icon in the menu bar to keep it visible.
Step 2: Play the video
- You: Play the video. If the window is captioning your microphone instead, click the Microphone icon in its corner, or choose Computer Audio from the Live Captions icon in the menu bar.
- macOS: Transcribes the speech into the Live Captions window as it plays.
- Check: Captions appear as people speak. Apple says their accuracy may vary and should not be relied upon in high-risk or emergency situations.
Apple lists two limits. Live Captions needs a Mac with Apple silicon, and it is not available in all languages, countries or regions. Its feature availability page lists English (Australia, Canada, India, Singapore, the United Kingdom and the United States), French (Canada and France), German (Germany), Japanese, Korean, Mandarin Chinese (China mainland and Taiwan), Cantonese (China mainland and Hong Kong), and Spanish (Mexico, Spain and the United States).
Make timed captions in Final Cut Pro
Final Cut Pro's Generate Captions turns the speech in your clips into captions with timings. It is Apple's route to a caption file, and it costs money and works only in U.S. English.
Step 1: Generate the captions
- You: In Final Cut Pro, select the clips with speech in the timeline, then choose Edit, Generate Captions, Closed Captions, or press Shift Command C.
- Check: Caption clips appear in their own lane at the top of the timeline. The first time, Final Cut Pro downloads its language model, so you need to be online once.
Step 2: Export them as text
- You: Convert the captions, which come out in the iTT format, to SRT, then export them as a separate file. Apple's guide covers both.
- Check: The SRT file opens in a plain text editor. Apple describes each caption in it as a number, a start and end time, and the text.
- Price. $299.99 as a one-time purchase, or included in Apple Creator Studio, which is free for 30 days and then $12.99 a month or $129 a year for new subscribers. Checked October 3, 2026.
- Mac. Final Cut Pro needs macOS 15.6 or later, and Generate Captions needs a Mac with Apple silicon.
- Language. Generate Captions works in U.S. English only.
So Final Cut Pro will happily caption your video, as long as everyone in it speaks U.S. English. Apple adds that background noise, music or people talking over each other can throw off the accuracy and timing, and suggests Voice Isolation and Noise Removal first.
Turn the video file into text with YapToText
YapToText reads the video file and transcribes its speech with Whisper Large v3 Turbo (Q5), the speech model inside the app, on your Mac. It is free on the Mac App Store, with no account. Drop the video on the card, and the words come back as plain text you can paste anywhere.
Step 1: Drop the video on the card
- You: Open YapToText and go to the Utility page. In the Transcribe a file card's mode menu, pick Raw Transcription for the words as spoken, or a mode such as Note to shape them. Then drop the video on the card, or click Choose File and pick it.
- YapToText: Recognizes the file by its content rather than its extension, transcribes the speech in it on your Mac and runs the mode you picked.
- Check: The text appears in the card. If an error shows instead, the ladder below has the fixes.
Step 2: Take the text
- You: Click Copy, or Insert to type the text into the app you were using before.
- YapToText: Hands over plain text. Send below passes it to the next card, which rewrites text through a mode such as Note or Clean Up.
- Check: The words are in your document.
What matters for video:
- Common formats. It reads anything macOS can decode. Containers it recognizes include MP4, MOV, M4V, 3GP, M4A, WAV, AIFF, CAF, FLAC, MP3 and AMR, and Ogg where macOS supports it.
- No minute cap. A file has no time limit and nothing is metered; the 30-minute safety stop applies only to a single live dictation. A video over 4 minutes is cut at quiet moments into pieces of about 2 minutes.
- 29 languages. The Language picker on the AI Models page lists 29 languages plus Auto-detect, and starts on your Mac's system language. The language guide lists them.
The same job is in the menu bar panel as Transcribe file and on the History page as Transcribe File. For a voice memo rather than a video, the guide to transcribing Voice Memos on a Mac starts with Apple's own transcript.

Compare the three ways
Checked October 3, 2026, on Apple's support pages and apple.com. Prices change, so check before you buy.
| Live Captions | Final Cut Pro | YapToText | |
|---|---|---|---|
| Cost | Free, built into macOS | $299.99 once, or Apple Creator Studio at $12.99 a month after a 30-day free trial | Free, no paid tier |
| Mac it needs | Apple silicon | macOS 15.6 or later; Apple silicon for Generate Captions | macOS 14 or later, Apple silicon |
| Works from | Audio playing on the Mac, or the microphone, as it happens | Clips in a Final Cut Pro timeline | A video or audio file |
| What you get | Captions in a window while it plays | Timed captions, exportable as an SRT file | Plain text to copy or insert |
| Timestamps | Not described | Yes, each caption is timed | No |
| Languages | 8 languages, in listed regions | U.S. English only | 29 languages plus Auto-detect |
| Where it runs | On device, per Apple | Not stated; the language model downloads once | On your Mac |
Live Captions is for following along, Final Cut Pro is for publishing captions, and YapToText is for the words themselves. Pick by what you want back: captions to watch, a caption file with timings, or plain text. If you would rather run Whisper yourself from Terminal, the guide to local Whisper on a Mac covers it.

If the video will not transcribe
Start with the file, then the settings. When in doubt, give YapToText the audio alone. Climb this ladder, smallest step first:
- Play it first. If you hear no speech, or only music, a speech model has nothing to transcribe.
- Export the audio alone. In QuickTime Player, choose File, Export As, Audio Only. Apple says that saves an MPEG 4 audio file with an AAC track, which you can drop on the card instead.
- Check for copy protection. If QuickTime Player's Export menu shows no options, Apple says the recording may be copyright-protected and cannot be distributed.
- Set the language. For a video in another language, choose that language or Auto-detect language in the Language picker on the AI Models page.
- Try a bigger speech model. Download one from the Dictation Model Library on the AI Models page and run the file again. A model download is the only network use the app starts.
The AI Models guide explains each model and its size.
What YapToText cannot do with a video
- Speaker labels. It does not say who is talking, so a conversation comes back as text with no names attached.
- Timestamps and subtitles. It adds no timestamps and exports no SRT or other subtitle file. For timed captions, Final Cut Pro is Apple's route.
- Translation as it transcribes. It transcribes what was said and does not translate it. To translate afterwards, select the text and ask Quick Edit for another language, or run Translate to English, one of the built-in AI Actions.
- Streaming video. It opens files on your Mac, so a video that only plays in a browser is not something it can read.
- Some Macs and builds. It needs macOS 14 or later on Apple silicon, and nothing is claimed for Intel Macs. The Homebrew build ships without the models and cannot transcribe until you download a speech model; the install guide covers that.
If who said what matters, the page comparing YapToText and MacWhisper for file transcription covers that difference, and the Quick Edit guide shows how to translate or shorten a transcript once it lands. YapToText gives you what was said, not who said it or when.

The short version
- For following along. Turn on Live Captions in System Settings, Accessibility, on an Apple silicon Mac.
- For a caption file with timings. Use Final Cut Pro's Generate Captions, in U.S. English, then export SRT.
- For the words as text. Drop the video on YapToText's Transcribe a file card, free and on your Mac.
The video goes in, the words come out, and nothing leaves your Mac. If a video will not transcribe and the ladder did not help, press Copy Diagnostics in Settings, About and open an issue on GitHub with the file type. Every issue gets read.
Download for free. No account, nothing locked, macOS 14 or later on Apple silicon. Source on GitHub.
Related
Sources
- https://support.apple.com/guide/mac-help/get-captions-of-spoken-and-computer-audio-mchldd11f4fd/mac (checked 2026-10-03)
- https://www.apple.com/macos/feature-availability/ (checked 2026-10-03)
- https://support.apple.com/guide/final-cut-pro/create-closed-captions-vere399dab5e/mac (checked 2026-10-03)
- https://support.apple.com/guide/final-cut-pro/intro-to-captions-ver00e40835d/mac (checked 2026-10-03)
- https://www.apple.com/final-cut-pro/ (checked 2026-10-03)
- https://support.apple.com/guide/quicktime-player/export-movies-qtp20e395859/mac (checked 2026-10-03)
- https://apps.apple.com/us/app/yaptotext/id6786382289 (checked 2026-10-03)
Questions
Can a Mac transcribe video to text?
Yes, in three ways. Live Captions shows real-time captions while a video plays on an Apple silicon Mac, Final Cut Pro generates timed captions in U.S. English, and YapToText turns a video file into plain text on your Mac for free.
How do I transcribe a video on my Mac for free?
YapToText. Open its Utility page, drop the video on the Transcribe a file card, and copy the text. It is free, transcribes on your Mac, and needs macOS 14 or later on Apple silicon.
Can I transcribe a video locally on a Mac?
Yes. YapToText transcribes the file with Whisper on your Mac and uploads nothing, and Apple says Live Captions processes audio on device. YapToText's only network use is a model download you start yourself.
Does YapToText add timestamps or speaker names?
No. It returns plain text, with no timestamps, subtitles or speaker labels. For timed captions, Apple's Final Cut Pro generates them in U.S. English and can export them as SRT.
Is there a length limit for transcribing a video in YapToText?
No. A file has no minute cap and nothing is metered; the 30-minute safety stop applies only to a single live dictation. A long video is cut at quiet moments and transcribed in pieces.