Sub-Video

Free MP4 subtitle generator

Drop in an MP4 and get timed subtitles back.

Initializing…

For a non-English language, set it yourself rather than auto-detect.

Whisper model

Downloaded once, then cached by your browser.

Generate subtitles for your MP4

Drag & drop an MP4 file here

or click to browse

Draws subtitles permanently into the frames (hardsub), locally via ffmpeg.wasm. Slow on longer videos.

Translates the text above in place, including your edits. Requires a specific “Spoken language”, not Auto-detect.

What this free MP4 subtitle generator does

Local Whisper Subtitles is a free subtitle generator that runs completely on your own device. It uses OpenAI’s Whisper speech-recognition model, compiled to WebAssembly and executed through Transformers.js, to turn the speech in a video into timed subtitles. Burning subtitles into the picture is handled by ffmpeg.wasm. Because both run in the browser, your video is never uploaded, there is no account or API key, and there are no file-size or minute quotas beyond what your own hardware can handle.

How to add subtitles to a video, step by step

  1. Choose language and download a model. Leave the spoken language on Auto-detect or pick it explicitly, then click the model you want: Tiny for speed, Base for a balance, or Small for the best accuracy. Nothing is downloaded until you click.
  2. Add your video. Drag an MP4 onto the drop zone or click to browse. The file is read locally.
  3. Transcribe. The model you downloaded is cached by your browser and runs in a Web Worker, so the page stays responsive.
  4. Edit and translate. Fix any misheard words straight in the subtitle box — the video preview updates as you type — and optionally translate the result to English or Swedish.
  5. Export. Download a .srt or .vtt file, or burn the subtitles permanently into a new MP4.

Features

  • Automatic speech recognition for MP4 video using Whisper tiny, base or small
  • Fully private: 100% client-side, no upload, no server, no tracking
  • Auto-detect or choose English, Arabic, Spanish, French, German, Hindi, Chinese, Russian, Portuguese or Turkish
  • Editable subtitles with a live preview on the video
  • Subtitle translation to English or Swedish
  • SRT and WebVTT export
  • Hardcoded (burned-in) subtitles via ffmpeg.wasm
  • Completely free — no sign-up, no watermark, no limits

Frequently asked questions

Is my video uploaded anywhere?

No. Transcription, translation and re-encoding all happen inside your browser using WebAssembly and, where available, WebGPU. There is no backend to send a file to.

Which subtitle formats can I download?

SubRip (.srt) and WebVTT (.vtt). You can also burn the subtitles into the MP4 as hardsubs so they show in any player, including ones that ignore sidecar subtitle files.

Which languages are supported?

Whisper can auto-detect the spoken language, and English, Arabic, Spanish, French, German, Hindi, Chinese, Russian, Portuguese and Turkish can be selected explicitly. Finished subtitles can be translated to English or Swedish.

Which Whisper model should I use?

Tiny (~75MB) is the fastest and leans English-only. Base (~145MB) is a good balance and handles non-English audio well. Small (~480MB) is the most accurate but noticeably slower. You pick which one to download — the page never fetches a model on its own.

Is it really free?

Yes — completely free, with no account, API key or usage cap, because all the computation runs on your own machine.

More on specific tasks

  • MP4 to SRT

    What an .srt file actually contains, why the conversion is really transcription, and how to fix timings and cue breaks in the output.

  • Add subtitles to an MP4

    Keeping subtitles as a separate file versus burning them into the picture — which one each platform needs, and what burn-in costs in quality.

  • Which Whisper model to use

    Tiny, base and small compared on download size, speed and the kind of audio each can cope with, plus how browser Whisper differs from the hosted API.

  • What “free” means here

    Why there is no minute cap, watermark or account wall — and, since every tool has a catch, exactly what you give up in exchange.

Learn how any of this works

Three referenced explainers on the machinery behind this tool — speech recognition, machine translation and the subtitle formats themselves. Every claim links to a primary source.

All articles →