Captionator

Captionator for Final Cut Pro

The easiest way to add high energy captions and titles to your videos. Automatic speech-to-text transcription with nearly 100 language support.

Download on the App Store

Features

Everything you need to create professional captions quickly

Automatic Transcription

Powered by Whisper and Siri engines for accurate speech-to-text conversion in nearly 100 languages.

Final Cut Pro Integration

Seamlessly exports captions and titles directly into your Final Cut Pro timeline.

Customizable

Control word lengths, timing, and choose from pre-built caption styling templates.

Runs Locally

All processing happens on your Mac. No cloud dependency, no data uploaded anywhere.

One-Time Purchase

No subscriptions. Buy once and own it forever with free updates.

100 Languages

Support for nearly 100 languages with the Whisper transcription engine.

Tutorial Videos

This tutorial series explains all of Captionator and how to create desired effects

Captionator Tutorial Playlist

Complete guide to using Captionator with Final Cut Pro

View Full Playlist

Ready to supercharge your captions?

Download Captionator from the Mac App Store today.

Download on the App Store

Frequently Asked Questions

Can it do multiple words per title?
Yes! Under the advanced options, you can set the minimum and maximum lengths of each caption or title.
Are languages other than English supported?
Version 2.0 includes nearly 100 languages via the Whisper engine. See the full language list for details.
Do I need a subscription?
No, Captionator runs entirely on your Mac. A one-time purchase will work forever!
I'm getting "Localization not found"
The large language model has a download bug from server changes. Use the Medium model, which has very similar accuracy, or wait for the next version fix.
Stuck at Processing in Version 2.0
On some Macs, if you use Whisper with CoreML, it doesn't error out, nor does it ever finish processing. Download alternative models without the CoreML addon. See this tutorial video for help.
It only transcribed the first 60 seconds
The Siri engine limits on-device support to certain languages. Unsupported languages require cloud transcription with a 60-second ceiling. It is best to use the Whisper engine for unlimited processing.
Transcriptions aren't very accurate
Captionator uses Whisper to dramatically increase accuracy. Install larger models (Small, Medium, Large) for improved results. See this tutorial for instructions.
It only detected a few words
Make sure to disable all music and SFX layers before you press the Export button to prevent speech recognition confusion.
Can I move the titles?
Move one title, copy it (Command-C), select remaining captions, then use Paste Attributes (Command-Shift-V) in the transforms panel. Alternatively, use the visual transform button beneath the preview pane.
How do I disable titles for a clean export?
Use the roles at the bottom left. Click "Index", then "Roles". Expand "Titles", and enable/disable "Generated Titles".
I don't see the Export option
Click Help > Captionator Help, then follow directions. Use "Install Export Destination" for express installation.
Do you collect my information?
No! We feel strongly that collecting your data is totally unnecessary for this type of application. App store operators may collect data; see their privacy policies or our privacy page.
Where can I get the fonts used in the standard styles?
Three licensed fonts are used: SF Pro Display, Trash Hand, and Komika Axis. Please verify licensing requirements before use.
I get a DTD Error when importing the captions
This is a Final Cut bug preventing valid FCPXML imports (possibly time machine-related). Solution: change the "DTD Ver" to something older in preferences.
Error: Failed to process audio: Timeout
This is usually cloud transcription-related. In Preferences, change the cloud setting to "Local Only" or switch to the Whisper engine for on-device processing.
I get blank_audio
Whisper is telling us that it can't understand the audio. The default tiny model struggles with imperfect audio; install larger models (Small or Base) for better results.

Need Help?

Check out the tutorials or join the community

Watch Tutorials Email Support