Generate Subtitles

Create original-language SRT or VTT subtitles from audio or video, then edit the words and timing.

Local fileText & subtitles

Drop your audio or video here

MP4 · WEBM · MOV · MP3 · WAV · M4A · OGG · OPUS · AAC · FLAC · Up to 200 MB / 20 minutes

Processed in your browser. No file upload.No signup · Free exports

What can Generate Subtitles do?

Subtitles pair readable text with playback times. Whisper provides word timing, and the tool groups it into segments. Review the start and end seconds, replay individual segments, and preview captions on an imported video. Keep the source recording available for checking.

How to use Generate Subtitles

Prepare your file, check the result, and download the format you need.

  1. 01

    Prepare your file

    Choose an audio or video file and select its spoken language.

  2. 02

    Process and review

    Run transcription, check each segment, and adjust its text and start/end seconds.

  3. 03

    Download your result

    Download SRT for an editor or player, or VTT for a web video.

Formats & example

MP4 · WEBM · MOV · MP3 · WAV · M4A · OGG · OPUS · AAC · FLAC → TXT / SRT / VTT

presentation.mp4 → review segments and times → presentation.srt

Protective limits: 200 MB and 20 minutes. Tested in desktop Chrome. Device performance and codecs affect processing; try a short clip first.

Your files stay in this browser

Whisper recognizes speech on your device. The first use downloads the program and model. Your files and transcript are not uploaded. Results are not saved automatically. Download before leaving.

Generate Subtitles: common questions

Useful answers before you begin.

Are captions burned into the video?

No. You get a separate subtitle file and an in-page preview. Import the file into a video editor to burn captions into a new video.

Does it translate subtitles?

By default, this tool produces original-language subtitles. You can also choose Translate to English. The language selector guides recognition; it is not a target translation language.

Is the timing always exact?

No. Music, noise, and overlapping voices can affect alignment. Listen back and adjust segment times before exporting.