You shot a decent video, it's clear, and it still goes unnoticed because nobody turns the sound on. Subtitling by hand easily eats up 30 to 45 minutes of work for 60 seconds of video: typing the text, breaking it into lines, syncing every line 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: with the built-in features of your phone and social apps, or with a dedicated third-party tool. You'll also see the settings that truly matter (text size, position, number of words per line) and the typical mistakes automatic transcription makes: bad line breaks, homophones, proper nouns. No technical skills required: 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 actually subtitles a video
A subtitling AI does three things: it listens to the audio track, it writes out the text, then it syncs each sentence to 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 option out there is Whisper, OpenAI's open source model, trained on 680,000 hours of multilingual audio. It's Whisper, or a variant of it, running under the hood of most tools you'll come across.
The second step is timestamping: the AI assigns a precise moment to every word (for example 00:00:04,120). That's what keeps subtitles from lagging half a second behind, the single most annoying flaw for the eye.
The third step is styling: font, size, color, word-by-word animation. At the end, you get one of two 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 turn subtitles on or off, and search engines can read the content.
- Burned-in subtitles (also called “hardcoded” subtitles): 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 usually starts muted.
For vertical formats, burning them in is almost always the right call. For a long video on YouTube or a website, keep the .srt file: it also feeds the page's search rankings.
Method 1: the built-in features of your phone and 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 and lets you fix each line before publishing. You can also generate translations. Styling is limited to a handful of presets.
On Instagram. Two routes: the “Captions” sticker you drop 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. After you upload the video, YouTube generates automatic 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 have a long shelf life. These subtitles get indexed, which is a real lever for an AI-powered faceless YouTube channel.
Straight on your phone. On iPhone, Apple's Clips app displays live captions while you talk and burns them into the video. On Android, several manufacturers offer transcription built into the gallery's editor, with availability that varies by model and OS version.
The limits of this route are always the same: styling is locked down, you don't get a file you can reuse elsewhere, and the transcription happens inside the app you publish on. If you're posting the same video across four platforms, you do the whole thing four times.
Method 2: dedicated 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 come across, in no particular order.
| Tool | Pricing model | Strength | Limitation |
|---|---|---|---|
| CapCut | Free with paid options | Lots of animated styles, fast vertical export | Watermark on some templates, cluttered interface |
| Submagic | Paid | Dynamic subtitles built for short-form | No lasting free version |
| Veed | Freemium | Edit in the browser, clean .srt export | Length and quality capped on the free plan |
| Descript | Freemium | Edit video by editing text like a document | Longer learning curve |
| Kapwing | Freemium | Translation and multilingual subtitling | Tight quotas on the free plan |
| Whisper (local) | Free, open source | No limits, works offline | Command-line installation |
Pricing for these services shifts 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 your computer. The trade-off is that you have to go through the terminal and wait longer if your machine doesn't have a dedicated graphics card. It's a good option for a high 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 speed. Professional subtitling standards sit around 17 characters per second and 42 characters per line for a horizontal video. Past that, the eye gives up. AI tools often break lines too finely or too coarsely: take a look at your longest lines before exporting.
Words on screen. In a vertical format, 3 to 5 words per screen with the spoken word highlighted works better than a full sentence. On a long 16:9 video, do the opposite: complete sentences across two lines, which is easier on the eye.
The safe zone. TikTok, Instagram, and YouTube Shorts overlay buttons, a handle, and a caption around the edges. Keep your subtitles between 20% and 70% of the frame 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 bar. Avoid bright colors on light backgrounds: it looks great on your calibrated screen and is unreadable in direct sunlight on a phone at 30% brightness.
These rules apply to any short-form content, including when you're mass-producing Reels and TikToks with AI.
Typical automatic transcription mistakes, and how to fix them fast
Automatic transcription trips up on four specific things: homophones, word boundaries, proper nouns, and numbers.
Proofreading 60 seconds of subtitles takes about two minutes. It's the best investment in the whole chain, because one glaring typo blown up in the middle of the screen costs you more credibility than a sloppy edit.
Your checklist:
- Homophones: there/their/they're, its/it's, your/you're, to/too. Models lean on context and get it wrong most often at the start of a sentence.
- Bad word boundaries: the AI can merge or split words in ways that make no sense, gluing a trailing consonant onto the next word. Scan for words that look oddly spelled or run together.
- Proper nouns, brands, and acronyms: your company name rarely comes through on the first pass. Many tools accept a custom vocabulary list: fill it in once and it works for all your videos.
- Numbers and units: “twenty-nine euros ninety” 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 of text with no periods or commas. At minimum, add the periods — they guide how lines get broken.
- Jargon and loanwords: words like “engagement,” “feed,” and “prompt” often come out spelled phonetically. Fix them to 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 after the animation is applied takes thirty.
Key takeaways
If you publish now and then, the subtitles built into TikTok, Instagram, or YouTube Studio are plenty and cost nothing. If you're putting out several videos a week, go through a specialized tool where transcription, styling, and export all live in one place: the time you get back is mostly on proofreading and republishing across platforms. Either way, stick to the rule of two minutes of proofreading per minute of video, keep your subtitles out of the interface zones, and cap yourself at two lines. The rest is just polish.
The simplest way to make up your own mind: subtitle a video you've already published using two different methods, and compare how long each one took.
