Automatically Subtitle a Video with AI, in French

You shot a decent video, it's clear, and it still goes unnoticed because nobody turns the sound on. Subtitling by hand is easily 30 to 45 minutes of work for 60 seconds of video: writing everything out, splitting it into lines, syncing each one to the speech. With a transcription AI, that same video comes back subtitled in 2 to 3 minutes, and all you have left is two or three words to fix.

This guide shows you two ways to do it in French: with the built-in features of your phone and the social apps, or with a specialized third-party tool. You'll also see the settings that genuinely matter (text size, position, number of words per line) and the typical mistakes automatic French produces: badly split liaisons, homophones, proper nouns. No technical skills needed: if you can drop a file into a window, you can do this. For the text part, starting with proofreading the transcript, you can get help from the Skilzy chat before going back to the subtitling tool of your choice.

How an AI subtitles a video, concretely

A subtitling AI does three things: it listens to the audio track, it writes the text, then it syncs each sentence with the exact moment it's spoken.

The first step is called automatic speech transcription. The model analyzes the sound and produces text. The best-known player in this space is Whisper, OpenAI's open source model, trained on 680,000 hours of multilingual audio, a large share of it French. It's Whisper, or a derivative of it, running under the hood of most of the tools you'll come across.

The second step is timestamping: the AI ties each word to a precise moment (00:00:04,120, for example). That's what keeps your subtitles from lagging half a second behind the voice, which is the single most irritating flaw for the eye.

The third step is styling: font, size, color, word-by-word animation. At the end of it, you get one of the two following formats.

• A separate subtitle file (.srt or .vtt): a plain text file you upload alongside your video on YouTube, LinkedIn or a website. Viewers can switch it on or off, and search engines read what's inside it.
• Burned-in subtitles (also called burn-in): the text is baked into the image. You can't turn it off, but it shows up everywhere, including on TikTok, Instagram and Shorts where playback often starts muted.

For vertical formats, burning them in is almost always the right call. For a long video on YouTube or a website, stick with the .srt file: it also feeds the page's search visibility.

Method 1: the built-in feature on your phone and the social apps

It's free, it's already installed, and for a story or a Reel you're publishing within the minute, it's often the best effort-to-result ratio out there.

No reason to hide this option: in plenty of cases, it gets the job done.

On TikTok. In the editor, open the right-hand menu, then Captions. The app transcribes automatically in French and lets you fix each line before publishing. You can generate translations too. Styling stays limited to a handful of presets.

On Instagram. Two paths: the Captions sticker you add on top of the video in the Reels editor, or the automatic captions option in your account settings, which turns them on by default. Editing is possible but less comfortable than on TikTok.

On YouTube. Once the video is uploaded, YouTube generates automatic French subtitles in YouTube Studio, under the Subtitles tab. You can edit them line by line or upload your own .srt file, which is the better move for a video you want to keep working for you. These subtitles get indexed, and that's a real lever for an AI-powered faceless YouTube channel.

On your phone directly. On iPhone, Apple's Clips app displays live subtitles as you speak and burns them into the video. On Android, several manufacturers offer transcription built into the gallery editor, with availability varying by model and system version.

The limits of this route are always the same: the styling is locked, you don't walk away with a file you can reuse elsewhere, and the transcription happens inside the app you're publishing on. If you're pushing the same video to four platforms, you do the whole thing four times.

Method 2: specialized third-party tools

These make sense when you want a highly polished look, batch processing, or a clean subtitle file to reuse.

Here are the families of tools you'll run into, in no particular order of preference.

Pricing for these services changes often: check the official page before committing, especially on annual plans.

A word on running Whisper on your own machine: it's the cheapest option per use and the most respectful of your files, since nothing leaves for a server. In exchange, you have to go through the terminal and wait longer if your computer has no dedicated graphics card. It's a good option for a large volume of sensitive content, not for subtitling a Reel between two meetings.

The settings that separate subtitles people read from subtitles people ignore

A subtitle is readable when it fits on two lines max, stays on screen long enough to be read, and doesn't hide behind the app's interface.

Four settings do most of the work.

Reading pace. Professional subtitling standards hover around 17 characters per second and 42 characters per line for a horizontal video. Past that, the eye gives up. AI tools often split things too finely or too coarsely: take a look at your longest lines before exporting.

Words on screen. On a vertical format, 3 to 5 words per screen with the spoken word highlighted works better than a whole sentence. On a long 16:9 video, do the opposite: full sentences over two lines, easier on the viewer.

The safe zone. TikTok, Instagram and YouTube Shorts stack buttons, a handle and a caption along the edges. Keep your subtitles between 20% and 70% of the image height, leaning toward the lower middle. A subtitle hidden behind the Subscribe button is useless.

Contrast. White text with a black outline, or text on a semi-opaque band. Avoid bright colors on a light background: it looks lovely on your calibrated screen and is unreadable in full sun on a phone at 30% brightness.

These rules apply to any short content, including when you're producing Reels and TikToks with AI in batches.

The typical errors of automatic French, and how to fix them fast

French trips models up on four specific things: homophones, liaisons, proper nouns and numbers.

Proofreading 60 seconds of subtitles takes about two minutes. It's the best investment in the entire chain, because one glaring mistake displayed in large type in the middle of the screen costs you more credibility than sloppy editing ever will.

The checklist:

• Grammatical homophones: a/à, ces/ses/c'est/s'est, et/est, ou/où, la/là. Models lean on context and mostly slip up at the start of a sentence.
• Badly split liaisons: les enfants ont attendu can come back as les enfants nont attendu. Watch for words that start with n' or t' for no reason.
• Proper nouns, brands and acronyms: your company name rarely lands on the first try. Plenty of tools accept a custom vocabulary list: fill it in once and it serves every video you make.
• Numbers and units: vingt-neuf euros quatre-vingt-dix is correct but unreadable as a subtitle. Rewrite it as 29,90 €. Same logic for percentages and dates.
• Punctuation and capitals: some models hand back a block with no periods or commas. At minimum, add the periods — they guide how lines get split.
• English loanwords: engagement, feed and prompt often get transcribed phonetically. Fix the spelling your audience expects.

One time-saving tip: proofread the text before you style it. Fixing a word in a text editor takes three seconds; fixing it once the animation is applied takes thirty.

What to take away

If you publish now and then, the subtitles built into TikTok, Instagram or YouTube Studio are enough and cost nothing. If you're producing several videos a week, go through a specialized tool where transcription, styling and export all live in one place: the time you win back is mostly on proofreading and republishing across platforms. Either way, keep the two-minutes-of-proofreading-per-minute-of-video rule, place your subtitles outside the interface zones, and cap yourself at two lines. The rest is comfort.

The simplest way to make up your own mind: subtitle a video you've already published, using two different methods, and compare the time it takes.