Guide16 November 20268 min read

How to add subtitles to a video on your Mac, offline, in 100 languages

Most subtitle tools upload your video to a server and charge by the minute. If you have an Apple silicon Mac, you can do the whole job on your own machine instead: transcribe the speech, split it into readable subtitles, translate them, and export files that YouTube and every major editor accept.

This guide walks through that process with MLX Caption, a Mac app I built for exactly this job. The first five videos are free, so you can follow along without paying. Near the end I also explain what happens under the hood, for anyone curious about running AI models locally.

Why do it offline?

What you need

MacApple silicon: M1, M2, M3, M4 or newer. Intel Macs can't run it.
macOS14 Sonoma or newer
Memory16 GB recommended. 8 GB works with smaller models, chosen automatically.
Disk8 to 15 GB free for the AI models, downloaded once
VideoMP4, MOV, MKV, WebM, AVI, or an audio file

Step 1: Download and open the app

Download the free trial from the MLX Caption page and unzip it. No account, email address or card is needed.

Because the app is sold outside the Mac App Store, macOS asks you to confirm the first time you open it. Open System Settings → Privacy & Security, scroll down and click Open Anyway. You only do this once, and the download includes a short guide with the exact steps.

Step 2: Let it download the models

On first launch the app installs its components and downloads the AI models: about 6.5 GB on Macs with 8 to 16 GB of memory, and about 13 GB on Macs with 24 GB or more. This is the only step that needs the internet. After that, everything works offline.

Step 3: Drop in a video and choose languages

The upload screen with a drop area and a language picker
The start screen: drop a file, pick languages, press start.

Drag your video onto the window. The spoken language is detected automatically. Then pick the subtitle languages you want. Fifteen common languages are selected by default, and there are buttons for "All core" (54 languages) and "All 100".

If your video has names or jargon the speech model might mishear, add them as a vocabulary hint. Then press start.

Step 4: Check the result

A video playing with Hindi subtitles next to the transcript and processing stats
Switch the subtitle language while the video plays. Click any transcript line to jump to that moment.

When it finishes you can play the video with any subtitle language, read the transcript, and compare a translation side by side with the original. It is worth a quick read before you publish, especially for names and for the less common languages.

For a sense of speed: on an M3 Pro, a 28-second clip was transcribed in 5.2 seconds. Translating that same clip into all 100 languages, plus scene descriptions and a summary, took 6 minutes 35 seconds. Older Macs and 8 GB machines are slower.

Step 5: Export and use the subtitles

Each job produces a folder with:

YouTube

In YouTube Studio, open Subtitles, choose your video, click Add language, then Add under Subtitles and choose Upload file → With timing. Select the matching .srt file. Repeat for each language. Viewers in other countries can then pick their own language.

Premiere Pro

Import the .srt file into your project like any other media, then drag it onto the timeline. It becomes a caption track you can restyle.

Final Cut Pro

Choose File → Import → Captions and pick the .srt file. Recent versions of Final Cut Pro import SRT directly.

DaVinci Resolve

Import the .srt file into the Media Pool, then drag it onto the timeline to create a subtitle track.

What happens under the hood

Everything runs on the Mac's GPU through MLX, Apple's machine learning framework for Apple silicon. Four models do the work, one at a time so memory stays manageable:

JobModel
Speech to textWhisper large-v3 turbo, with timing for every word
Translation and summaryGemma 3 12B, 4-bit
Scene descriptionsQwen3-VL, one keyframe per shot
Silence and shot detectionSmall custom routines written directly in MLX

The interesting trick is in translation. Generating text on a GPU is limited by memory bandwidth, not by raw compute, so translating into 16 languages in one batch costs little more than translating into one. The app reads the shared part of each prompt once, then decodes all the target languages together. That is why adding languages is cheap.

Two smaller details make the output usable. Silent stretches are skipped, because speech models tend to invent text in silence. And every translated line is checked for letters from the wrong writing system, for example Hindi script inside Urdu, and translated again if needed.

Limits worth knowing

Disclosure: I am the developer of MLX Caption. After the five free videos it costs $49 once, with a 14-day refund. There is no subscription.

Try it on your own video

Your first 5 videos are free, with every feature. Nothing is uploaded.

Download the free trial ↗

Questions, or need something built? Email me at hello@tabishapps.com. I am Tabish Hassan, a software developer in Pakistan, and I build websites, apps and business systems.