PartPriced Tools

Transcription · free, in your browser

Make subtitles (SRT or VTT) from a video

Drop a video or an audio track and get a subtitle file with a start and end time for every line. Whisper listens on your device, so the footage is never uploaded.

Make subtitles

How to do it

  1. Open Transcription from this page: the format is already set to Subtitles (.srt). The first time, press Get more… and confirm the download of the Whisper tiny model (about 40 MB). It is kept in your browser for next time.
  2. Drop the video or audio file on the page and press Transcribe.
  3. Turn on Show times to check each segment with its start time.
  4. Keep Subtitles (.srt), or choose Web subtitles (.vtt) for HTML5 video, and press Download.
  5. Load the file in your video player or editor next to the video.

Subtitle files keep the segments exactly as Whisper heard them, with its timing. Corrections typed in the text box go into the Text and Word downloads, not into the subtitles; an SRT file is plain text, so a text editor can fix a line after you download it.

Your files stay on this device: Transcription runs in your browser, with no upload, no account and no watermark.

Questions

What is the difference between SRT and VTT?

Both are plain-text subtitle files with a start and end time for each line. SRT is the most widely accepted; WebVTT (.vtt) is the format HTML5 video players read.

Can I edit the subtitles here?

Not line by line. Corrections in the text box apply to Text and Word only; SRT and VTT keep the timed segments as the model heard them.

Which languages work?

Choose one of the 99 languages Whisper knows in the Spoken language list, from Afrikaans to Yoruba, including English, Spanish, French, German, Chinese, Japanese and Arabic, or leave it on Detect. The subtitles are in the spoken language; there is no translation.

Is my video uploaded?

No. The sound is read and transcribed in your browser. Only the Whisper model is downloaded, once, from Hugging Face, and then kept in your browser.

More with Transcription

  • AI Tools
    Beta
    OCR, speech to text, denoise, auto tags and portrait blur. On your device.
  • Video Editor
    Beta
    A video editor that never uploads your footage.
  • Video Remix
    In development
    Clips and photos in, an automatic edit out, then fine-tune in the video editor.