Skip to content
TranscriptionClip

Automatic Subtitle Generator

Create captions for your video in minutes. Each caption is timed from the speech in your file, and you can edit every line before downloading an SRT or VTT file.

Drop a video or audio file here

or

MP4, MOV, M4V, WEBM, MKV, AVI, MP3, WAV, M4A, AAC, OGG, OGA, OPUS, FLAC · up to 500 MB

By default, captions are generated in your browser and your file never leaves your device. If you choose to process it on our server instead, it is uploaded over an encrypted connection and deleted once its audio is extracted. The caption preview always plays your video locally in your browser. Privacy policy

How to use Subtitle Generator

  1. 1

    Upload video or audio

    MP4, MOV, WebM, MKV, MP3, WAV, M4A and more — up to 500 MB and 60 minutes.

  2. 2

    Choose a caption layout

    Pick characters per line and one or two lines per caption to suit your video.

  3. 3

    Edit, preview, download

    Fix wording, watch the captions on your video, then save SRT or VTT.

SRT or VTT: which should you download?

SRT (SubRip) is the most widely supported caption format. Use it for YouTube, Facebook, LinkedIn, Vimeo, Premiere Pro, Final Cut Pro, DaVinci Resolve and most desktop players such as VLC.

VTT (WebVTT) is the web standard used by the HTML <track> element and by many online course platforms and video hosts. If you are adding captions to a website's own video player, choose VTT.

Both files contain the same captions and timings. You can download both and decide later.

How captions are timed

The speech recognition model returns timestamps for the speech it hears. The generator groups words into captions using common readability guidelines: it starts a new caption when a line would exceed your chosen length, when a caption would stay on screen longer than about six seconds, when the speaker pauses, or at the end of a sentence. Two-line captions are split near the middle so both lines are balanced.

Choosing a caption layout

  • 42 characters, up to 2 lines is the standard for landscape video and matches what broadcast and streaming captions typically use.
  • 32 characters, 1 line works well for vertical video on TikTok, Instagram Reels and YouTube Shorts, where wide captions cover too much of the frame.

You can change the layout after generation; the captions are rebuilt from the same timings without processing the file again.

Burn captions into your video

When captions need to be always visible, as on TikTok, Instagram Reels and YouTube Shorts, the studio can also export a copy of your video with the captions burned in. Choose a caption style and font, drag the caption to where you want it in the frame, and pick an output resolution. The export runs in your browser in real time, so keep the tab open until it finishes. It works in browsers that can record video, such as Chrome and Edge.

Supported formats and limits

Upload a video or audio file (MP4, MOV, M4V, WEBM, MKV, AVI, MP3, WAV, M4A, AAC, OGG, OGA, OPUS, FLAC) up to 500 MB and 60 minutes long. Captions are created in the language that is spoken; translating them into another language isn't available yet.

Accessibility

Accurate captions make your videos usable by people who are deaf or hard of hearing and by anyone watching with the sound off. Automatic captions are a strong first draft — review names, numbers and technical terms before you publish. Already have a subtitle file and just need the words? Use SRT to TXT.

Frequently asked questions

How do I add the SRT file to YouTube?

In YouTube Studio, open your video, choose Subtitles, select the language, then choose Upload file and pick “With timing”. Select the SRT file you downloaded.

Can I edit the subtitles?

Yes. Every caption is editable before you download. Your changes are included in both the SRT and VTT files and shown immediately in the preview player.

Does the tool burn subtitles into the video?

Yes, if you want. Besides separate SRT and VTT files, the studio can export a copy of your video with the captions burned in, using the style and position you see in the preview. The export runs in your browser in real time, so it takes about as long as the video, and the tab must stay open. It works in browsers that can record video, such as Chrome and Edge; depending on the browser, the file is MP4 or WebM. For YouTube and video editors, separate subtitle files are still the better choice because they can be corrected later.

Can it translate subtitles into another language?

Not yet. Captions are created in the language that is spoken in the file. Translation is planned for a future version.

How accurate are the timestamps?

Captions are aligned to timestamps from the speech recognition model, so they usually appear close to the speech. Processing on our server can use word-level timings for tighter sync. Use the preview to check sync before publishing.

Is there a length limit?

Files can be up to 60 minutes and 500 MB. When you process files on our server, there is also a daily per-visitor limit on total transcription minutes to keep the free tool available.

Related tools