---
title: "How to add subtitles to a video | ToolSugar"
description: "Generate SRT, VTT or text subtitles from speech, or burn captions into an MP4. It runs a Whisper model in your browser and uploads nothing."
canonical: https://toolsugar.com/blog/how-to-add-subtitles-to-a-video
image: https://toolsugar.com/og.png
---

# Add subtitles to a video with automatic captions

Updated 2026-11-09

To add subtitles to a video, transcribe the speech into timed lines and save them as a caption file or draw them onto the picture. Auto Subtitles does both in your browser, and the file is never uploaded. Drop a video or audio file, download SRT, VTT or text, and burn the captions in if you want.

[Open Auto Subtitles](https://toolsugar.com/tools/subtitle-generator)

## Add subtitles in three steps

Video and audio files both work. A recording that mixes languages is the one case where you should set the language yourself.

1. Drop your file.
2. Leave the language on Detect automatically, or pick one.
3. Download the SRT, VTT or text file. For a video, you can then burn the captions into a new MP4.

## SRT, VTT or burned in

SRT and VTT are small text files with a time for each line. A player reads them and viewers can switch the captions on or off. Use SRT for a YouTube upload and VTT for an HTML5 player or a course platform.

Burned-in captions are part of the picture, so they show on every device and cannot be turned off. That suits a muted social clip. The tool writes them into a new MP4.

## Speech recognition on your device

Whisper runs inside your tab, so the audio and the picture stay on your computer. The first run downloads a speech model of about 77 MB, or 206 MB with WebGPU, then reuses the saved copy. Hindi needs a larger model.

Speed depends on your device, and long files are slow on weak ones. Noisy audio gives more mistakes, so check the text before you publish. Each run counts toward the 5 free AI runs you share across tools in any rolling 24 hours, with no sign up.

## Burned-in text in other scripts

The tool ships Noto Sans and Noto Sans Devanagari, which cover Latin, Greek, Cyrillic and Devanagari text. For Japanese, Arabic, Korean and similar scripts it tells you it cannot draw the words. The SRT and VTT files still work in those languages.

## Questions

### What if my recording uses two languages?

Pick the language yourself instead of using automatic detection. Detection listens to the start, so a switch halfway through can confuse it.

### How long does it take to burn captions in?

The tool re-encodes every frame on your device. A short 360p clip finished in about real time in our test. A 1080p video takes much longer than its own length.

### Can I make subtitles from an audio file?

Yes. You get the SRT, VTT and text files. Burning is only offered for video files.

[Open Auto Subtitles](https://toolsugar.com/tools/subtitle-generator)

## Related guides

- [How to transcribe audio to text](https://toolsugar.com/blog/how-to-transcribe-audio-to-text)
- [How to translate a video](https://toolsugar.com/blog/how-to-translate-a-video)
- [How to trim a video without re-encoding](https://toolsugar.com/blog/how-to-trim-a-video)
- [How to dub a video with AI](https://toolsugar.com/blog/how-to-dub-a-video-with-ai)
- [How to remove music from a video](https://toolsugar.com/blog/how-to-remove-music-from-a-video)

## Comparisons

- [Kapwing alternative](https://toolsugar.com/alternatives/kapwing-alternative)
- [VEED alternative](https://toolsugar.com/alternatives/veed-alternative)
- [CapCut alternative](https://toolsugar.com/alternatives/capcut-alternative)