Support

Turn speech into text, and text into shareable video clips – right on your Mac.

Requirements

Mac with Apple silicon (M1 or later) and macOS 26 or later
About 2 GB of free disk space for the speech recognition model

Getting started

Open Ordagrant and click Download Model (about 1.6 GB, only once).
Drag an audio file into the window, or open one with ⌘O.
Correct the text if needed, select the words you want and click Export Clip.

Frequently asked questions

Is my audio sent anywhere?

No. All transcription happens on your Mac. The only thing the app downloads from the internet is the speech recognition model on first launch.

Which languages are supported?

Swedish, English, Norwegian, Danish, Finnish, Icelandic, German, French, Spanish, Italian, Dutch, Polish and Portuguese. You can also let the app detect the language automatically. For best results, choose the language before opening the file.

Which audio formats can I use?

Common audio formats such as MP3, M4A, WAV and AIFF.

The first launch takes a long time – is something wrong?

After the download, the model is optimized for your Mac's chip. This takes about a minute and only happens once.

A word is missing or wrong. How do I fix it?

Double-click the word in the table to listen. Edit it directly in the table, right-click to remove, add or merge words, and use ‹ › to fine-tune its timing. You can undo everything with ⌘Z.

Which video formats can I export?

9:16 (TikTok, Reels, Shorts), 4:5 (Instagram feed), 1:1 and 16:9 (YouTube). Turn on Safe Zones in the preview to see where each platform's buttons appear.

Are my corrections saved?

Yes, automatically. If you open the same audio file again, your corrections are loaded right away, even if the file has been moved or renamed.

How do I change the app's language?

Open Settings (⌘,), choose a language and restart the app.

Found a bug or have a question? Write to me and I'll get back to you.

Email me