A free video caption generator that writes captions word by word and burns them into your video, or saves SRT and VTT, on your own device.
Drop a video, and Whisper writes the captions on your device. Fix any word, pick a look, and burn them into the video, or download SRT and VTT.
Add your video
Whisper doesn't tell speakers apart, and it can mishear names, so read the captions before you burn them in. The video and its sound stay on your computer unless you pick On our server.
This free video caption generator writes captions for any video and burns them into the picture, on your own device.
Whisper writes every word with its time, you fix any it misheard, and you pick one of five looks. Nothing is uploaded, and there's no watermark.
Here's how it works, which look to pick, and how to get the caption files too.
What is a video caption generator?
A video caption generator turns what's said in a video into on-screen text, timed to the speech. This one draws the words into the video itself, so they show on every app, with the sound on or off.
It runs Whisper, OpenAI's speech recognition model, in your browser, with a time for every word.
Fix the words first
Whisper writes what it hears, and it can mishear a name or a brand. Every caption is listed with its time: click one, fix it, and click away.
The fixed words keep their place in time, so the colored word still moves with the speech.
Five caption looks
| Look | What it does | Good for |
|---|---|---|
| Bold | Heavy letters with an outline, the word being said in color | TikTok, Reels and Shorts |
| Box | Plain letters on a dark box | Talking heads, busy backgrounds |
| Karaoke | Words change color as they're said | Songs, quotes, slow speech |
| Clean | Plain letters with a soft shadow | LinkedIn, interviews |
| One word at a time | Each word alone, big | Fast, punchy clips |
Pick the font, the size, the height and the color of the word being said. The preview plays with the sound, so you see each word land.
Burned in, or a caption file
Burned-in captions are part of the picture: they show everywhere, and nobody can turn them off. That's what most short videos use.
A caption file sits next to the video instead. YouTube Help lists SubRip (.srt) and WebVTT (.vtt) among the files it takes, and both download here.
Change the size too
Keep the video's own size, or pick a platform's, like TikTok's 1080 x 1920. The captions are laid out for the new shape, with the video's blurred copy behind it or cropped to fill.
The sizes come from each platform's own page, the same table as the video resizer.
On your device or on our server
Whisper runs in your browser by default: Standard is a 77 MB download, Best 563 MB on browsers with WebGPU. For long videos, On our server writes the words in seconds and doesn't keep the sound.
Nothing is uploaded
On this device, the video never leaves your computer: your browser reads it, draws the captions on each frame and saves the new file.
After you caption
Post it, or cut it to size with the video resizer. For the words as a document, use the video to text converter.
Who is the video caption generator for?
It's for anyone posting videos that people watch without sound:
- Video to text converter – people who want the transcript too
- Video resizer – creators posting on several platforms
- Audio translator – anyone reaching viewers in another language
- Audiogram generator – podcasters turning audio into captioned clips
More tools like these are on my free tools page.
Video Caption Generator FAQs
Questions about the video caption generator? Here's what to know.
A video caption generator turns what's said in a video into on-screen text, timed to the speech.
This one draws the captions into the video itself, in your browser.
Drop the video here, click Write the captions, then Burn in the captions.
There's no account and no watermark.
Yes, every caption is listed with its time, and you can type over any of it.
The fixed words keep their place in time.
Yes, download SRT or VTT next to the captions list.
YouTube takes both.
Any language Whisper knows, detected from the first words or picked from the list.
Pick the language when you know it: names and short clips come out better.
Yes, it's free, with no account and no watermark.
On your device there's no limit; on our server, each visitor gets 40 minutes a day.
No, not on this device: Whisper and the video maker run in your browser.
On our server, only the sound is sent, in pieces, and it isn't kept.
This video caption generator is for anyone posting video people watch with the sound off:
- Video resizer – creators posting one video in several sizes.
- Podcast transcript generator – podcasters who clip their episodes.
- Video to text converter – anyone who needs the words as text too.
Teachers and course creators use it to make lessons easier to follow.
I did.
I'm Navid Moazzez, and the video caption generator is one of my free tools on navid.me.
Read more about me.
There's a video caption generator, an audiogram generator, an audio to video converter, a video resizer and a video to text converter.
The rest are in free tools.
Navid Moazzez
AI business strategist & AI OS builder
Navid Moazzez helps creators and founders master AI and build their own AI Operating System (AI OS) to automate their business and life.
Navid.me is reader-supported. When you buy through links on this site, I may earn an affiliate commission. Learn more.
More free tools
TikTok
Instagram
YouTube
X
Bluesky
LinkedIn
Threads
Mastodon
Pinterest
Amazon KDP
Apple Books
Amazon
Spotify
Apple Podcasts
Free AI newsletterThe most actionable AI newsletter for founders
Every week, get proven AI strategies, curated tools, and step-by-step systems to grow your audience, create better content, and build a profitable creator business.
No fluff, no filler, no BS. Just five minutes each week that might level up your online business and life.
P.S. Sign up now to get free access to my ultimate AI tools guide for creators.
