Subtitle generator

Add Subtitles to Video (auto or manual)

Auto from audioEdit inlineBurn-in or SRT

There are two ways to add subtitles to a video. Generate them from the audio (auto-caption), or write them yourself based on a script you already have (manual). This page does both. Auto-caption is the default path because it is faster, and the inline editor lets you fix any words the model got wrong. Manual is available for cases where you do not have audio, or where you want a translation that does not match the spoken words.

Drop your video or audio file here

or click to browse

Supports video and audio files up to 2048MB

About Add Subtitles to Video

The output options cover the common cases. Burn the subtitles into the video for platforms that strip or hide opt-in captions. Export SRT for YouTube, Vimeo, and most editing software. Export VTT for embedded HTML5 video on a website you control. The same transcription run produces all three, so you do not have to pick which output you want before you start.

What this page does not do is grab subtitles from a streaming service or a DVD. That is a different workflow that requires source files we do not have. If you are looking to extract embedded subtitles from an MKV, a desktop tool like MKVToolNix is the right path. For everything else (auto-generating, editing, styling, and exporting subtitles for video you own), this page covers it.

When this fits

Marketing videos for the web

Sound-off viewing dominates social and most web embeds. Subtitles on every video are the cheapest engagement win available.

Internal training

Onboarding videos and product demos benefit from subtitles for accessibility, for non-native speakers, and for noisy office environments.

Course content

Online courses with subtitles see higher completion rates and serve a wider audience. The auto-flow produces a starting point that the instructor cleans up.

Translation prep

A clean source-language transcript is the input that translators work from. Generate it here, then hand the SRT to a translator for localisation.

How to add subtitles to a video

1 Drop the video

Upload the file. It stays on your device the whole time.

2 Auto-generate from audio

Whisper produces a time-coded transcript. Edit it inline to fix mistakes or rewrite for translation.

3 Style the subtitles

Pick a styling preset or customise font, color, position, and background. The live preview shows what the burn-in will look like.

4 Burn in or export

Download the burned-in MP4, the SRT sidecar, or the VTT for HTML5 video. The same run produces all three.

Frequently asked questions

How do you add subtitles to a video file?

Drop the video on this page. Whisper transcribes the audio in your browser, producing time-coded subtitle text. You edit any wrong words, style the subtitles if you plan to burn them in, then export. The export options are burn-in MP4, SRT sidecar file, or VTT for HTML5 video.

Can I add subtitles manually instead of auto-generating?

Yes, by way of the inline transcript editor. After Whisper produces an initial pass, you can rewrite every line, delete segments, or merge them. If your audio is unintelligible or non-existent (silent video, music-only), start with the auto-generated empty transcript and type each line manually with timecodes set in the editor.

What is the difference between subtitles and closed captions?

Subtitles transcribe spoken dialog and are aimed at viewers who can hear the audio but want the text (often for translation or noisy environments). Closed captions add non-speech audio cues like [door slams] and speaker labels for deaf and hard-of-hearing viewers. The closed-captions page covers the second workflow specifically.

Can I add subtitles in a different language than the audio?

Translation is not built into this page. The workflow is: generate the source-language SRT here, then translate the SRT in a tool like Google Translate, DeepL, or by paying a human translator. Bring the translated SRT back to a video editor to burn it in or attach it as a sidecar file.

How long does adding subtitles take?

For a 5-minute video, around 30 to 60 seconds for the transcription pass plus however long you spend editing. For a 60-minute video, 5 to 10 minutes of processing plus the editing pass. The burn-in step adds about 1x to 2x of the video duration on top.

Your video never leaves your device

All processing happens locally in your browser, and your files never leave your device. The page reads your video through a standard browser file input, holds the bytes in memory, runs Whisper for speech recognition in a Web Worker, and writes the captioned MP4 back to your disk. No upload, no cloud transcription queue, no external copy.