Captions keep people watching. Many viewers scroll with the sound off, and big, bold words on screen make a Reel easier to follow and harder to skip. This auto caption generator adds those captions for you, free and with no watermark, so the finished video looks like your work, not an advert for an app.
Auto caption generator (free, no watermark)
Add bold, Reel-style captions to a short video in your browser: transcribe, fix any words, pick a style with a red word-by-word highlight, and download the video with no watermark.
- No upload
- No watermark
- No sign-up
- Free
Choose your video
Speed and data options
Models are saved in your browser after the first download so you don't pay for the data twice.
Your file never leaves this device: speech recognition (OpenAI Whisper) runs inside your browser. Only you must have the rights to the media you use. Keep this tab open while it works.
Check and edit
Download
Burn captions into your video
Videos up to 60 seconds, saved at up to 720p with no watermark. Rendering takes about as long as the video.
How it works
- Choose an audio or video file from your phone or computer. It is read by your browser only; nothing is uploaded.
- Pick the spoken language and a model. Tiny is fastest; Base is more accurate but needs a stronger device. The first time you use it, your browser downloads the model once (about 41 MB for Tiny or 77 MB for Base) and keeps it for next time. Use Wi-Fi for that first download if data is expensive.
- Whisper turns the speech into text with timings, about 30 seconds of audio at a time, and you can watch the progress.
- Fix any wrong words or timings in the editor, play a line to check it, and choose short Reel-style captions or longer subtitle lines.
- Download TXT, SRT or VTT files, or burn the captions into a video of up to 60 seconds with no watermark.
Frequently asked questions
Is it really free with no watermark?
Yes. Transcripts, subtitle files and burned-in captions are free, with no sign-up and no watermark. You can add a small "Captions: centertainment.site" credit if you want to, but it is off by default. It costs us nothing because the work happens on your own device.
What caption styles can I use?
Red highlight (each word lights up in red as it is spoken), red box, classic white on black, and white outline. You can set the size, put captions at the top, middle or bottom, show them in capitals, and choose short captions of a few words for Reels and TikTok.
What format is the captioned video?
MP4 where your browser supports recording it (recent Chrome, Edge and Safari), otherwise WebM. Instagram, TikTok, YouTube and WhatsApp accept MP4. If you get WebM and an app refuses it, convert it or use the SRT file in CapCut or VN instead.
Why does burning captions take as long as the video?
Your browser plays the video once while drawing the captions on every frame and recording the result, so a 45-second clip takes about 45 seconds. Keep the tab open and on screen until it finishes.
How long can my file be?
Up to 30 minutes for transcription and up to 60 seconds for burned-in captions (exported at up to 720p). On older phones we recommend files under 10 minutes and the Tiny model. Longer files, batch jobs and 1080p are planned for Caption Studio Pro.
Is my audio uploaded anywhere?
Your audio and video never leave your device. The speech recognition model (OpenAI Whisper) is downloaded to your browser and runs there, so nothing is uploaded to Centertainment or anyone else. The only downloads are the model files (from Hugging Face) and the speech engine (from the jsDelivr CDN), which your browser fetches like any other web file.
Choose a short video from your gallery, and the generator listens to it, writes the words and lines them up with the speech. Before you export, you can correct any word it got wrong, which matters for names, slang and brand names. Then pick a look and save the captioned video.
Caption styles
- Red highlight: white text with each word lighting up in red as it’s spoken, the karaoke-style look popular on Reels and TikTok.
- Red box: white words on a solid red block that stands out on busy footage.
- Classic: white text on a dark strip, best for interviews and talking-head videos.
- White outline: clean text with a heavy black edge, readable on any background.
You can also choose small, medium or large text, put the captions at the top, middle, lower third or bottom, and show them in capitals. Short captions of one to four words are the default because they’re easiest to read on a phone screen.
What to expect
The free version captions videos of up to 60 seconds and saves them at up to 720p. Your browser plays the video once while it draws the captions, so a 30-second clip takes about 30 seconds to render; keep the tab open while it works. Most browsers save MP4, and some save WebM. If an app won’t accept your file, download the SRT subtitle file instead and add it in CapCut or VN.
A small "Captions: centertainment.site/" credit is available if you'd like to give us a shout-out, but it's off unless you tick it. Have a longer video or just need text? Use the SRT subtitle generator or video to text.