Skip to content

Subtitle generator (SRT and VTT)

Generate SRT or VTT subtitles from a video on your device with Whisper: timed, two-line cues you can edit before downloading.

Loading tool…

Drop a video or audio file hereMP4, MOV, WebM, MKV, MP3, M4A, WAV, OGG and more · up to 500.0 MB and 60 minutes on this device
  • Your audio never leaves this device: it is decoded and recognised inside this browser tab.
  • The first run downloads the speech model (44 MB fast, 81 MB more accurate, 247 MB best) and keeps it in your browser for next time.
  • Keep this tab open until it finishes. Long files take a while; speed depends on your computer.
  • Works best in Chrome or Edge on a desktop or laptop.

How it works

Create subtitles for a video without uploading it. Whisper, OpenAI's open speech-recognition model, runs in your browser to recognise the speech with timestamps; the tool then cuts it into subtitle cues of at most two lines of 42 characters and 7 seconds on screen, the common broadcast and streaming guideline. Review the text next to the video, fix any line, and download a SubRip (.srt) or WebVTT (.vtt) file, or the video itself as an MP4 with a switchable subtitle track or with the captions burned in.

SRT is the most widely accepted format: YouTube, Facebook, LinkedIn, VLC, Premiere Pro, DaVinci Resolve and most TVs read it. WebVTT is the web standard used by the HTML video element and many online players. Both files use UTF-8 so Arabic and other scripts display correctly, and the SRT gets a byte-order mark when it contains non-Latin text so older Windows players pick the right encoding. Timings come from the model's own timestamps and are usually within a fraction of a second, but check the start of each scene.

Choose Fast (Whisper tiny, about 44 MB downloaded once), More accurate (Whisper base, about 81 MB) or Best (Whisper small, about 247 MB, recommended for Arabic). In our test on a single 2.1 GHz processor core, Fast handled English speech at about 4 times real speed and More accurate at about 2 times, so a 5-minute clip is ready in roughly 1.5 or 2.5 minutes; Best ran at about 0.6 times real speed. Whisper can also produce English subtitles for speech in any of its 99 languages. Files up to 60 minutes work on a computer (Chrome or Edge recommended) and 20 minutes on a phone.

How to use it

  1. Choose or drop your video (MP4, MOV, WebM, MKV and more).
  2. Set the spoken language, pick Fast or More accurate, and tick "Translate the speech into English" if you want English subtitles for another language.
  3. Click Generate subtitles and watch the lines appear as the video is processed.
  4. Play each line from its timestamp and correct names, numbers and spelling in place.
  5. Download SRT or VTT for YouTube or your editor, or an MP4 with the captions for social apps.

Frequently asked questions

SRT or VTT: which should I download?

SRT for YouTube, social networks, video editors and TVs; VTT for websites using the HTML5 video player. They carry the same text and timings. SRT writes milliseconds after a comma (00:01:02,500) and VTT after a dot (00:01:02.500).

Are the subtitles timed correctly?

Timings come from Whisper's timestamps, usually accurate to within a fraction of a second. Long sentences are split into shorter cues and their time is shared out by length, so check fast dialogue and scene changes in the preview before publishing.

Can I get English subtitles for a video in another language?

Yes. Tick "Translate the speech into English" and Whisper writes English subtitles directly from speech in any of its 99 languages. It cannot translate into other languages.

Is my video uploaded?

No. The audio is extracted and recognised inside your browser tab; only the speech model is downloaded, once, from this site.

Can I burn the subtitles into the video?

Yes. "MP4 with captions burned in" draws them into the picture (white text on a dark box, Arabic joined and right to left), so they show on WhatsApp, Instagram and TikTok. It re-encodes the video on your device at roughly real-time speed for 720p, up to 30 minutes on a computer. "MP4 with subtitles" instead adds a switchable track in seconds.

Can I turn off the short cues?

Yes. Untick "Split into short subtitle lines" to keep one cue per recognised segment, which suits transcripts shown beside a video more than on-screen captions.

Related tools