A free alternative to CapCut auto captions
Subtrims is free, English-only, and runs speech-to-text locally in your browser. No credit card needed.
When you need captions outside one editor
Auto captions inside an editor are convenient when you also finish the video in that editor. But if you cut in Premiere Pro or another editor, or want a portable subtitle file you can reuse, you need the captions as an SRT file. That is what Subtrims makes.
What Subtrims does
- Transcribes English speech locally in your browser.
- Splits the transcript into short captions of 2 to 5 words, using word count, punctuation and pauses.
- Offers an optional ALL CAPS mode.
- Lets you click any caption to edit it.
- Exports SRT with timecodes or plain TXT.
How it differs
Subtrims is a subtitle-file tool, not a video editor: it does not burn captions into your video or style them. You bring the SRT into your editor of choice and style it there. In exchange you get a file that works across compatible editors, and your media stays on your device.
What the file looks like
Each caption in an SRT is a number, a start and end time (hours:minutes:seconds,milliseconds), the text, and a blank line. Here is a short illustrative example of 3-word captions where punctuation ends a caption early:
1
00:00:00,000 --> 00:00:01,200
YOU HAVE A STORY.
2
00:00:01,200 --> 00:00:02,600
MAKE EVERY WORD
3
00:00:02,600 --> 00:00:03,500
COUNT.
Who it suits
Editors in Premiere Pro who want a quick caption track, creators who repurpose one clip for TikTok, Reels and Shorts, and anyone who wants a transcript of a short clip without paying. No credit card is required.
Which files to upload
Try MP4, MOV, WebM, MP3, WAV, M4A or OGG. Decoding support depends on your browser and the media codec. If a video cannot be read, export its audio as WAV or MP3 and upload that instead. Short clips work best.
Limits worth knowing
The free version handles English clips up to 5 minutes and 100 MB, with no credit card needed. There is no translation. The first run downloads the speech model, so it can take a few minutes; later runs reuse the cached model. Accuracy is best with clear speech: background noise, overlapping speakers, names and accents can cause mistakes, so skim the captions before exporting.
Privacy
Your media is decoded and transcribed locally on your device. The site does not upload or store your audio or video, which makes Subtrims a good fit for client footage or interviews you would rather keep off third-party servers.