Video to SRT

Turn any video into a ready-to-use .srt subtitle file, generated by AI.

More accurate, slower — recommended

The first run downloads the speech model to your browser (cached after that). Best on desktop — mobile devices may be slower.

Drop a video or audio file to transcribe

or click to browse

Processed on your device — never on a server.

How it works

1

Drop a video or audio file in. WavyVid decodes the audio track right in your browser, no upload involved.

2

An AI speech-recognition model (Whisper, running fully on-device via WebAssembly/WebGPU) transcribes the audio into timestamped text, segment by segment.

3

Edit the transcript if any words came out wrong, then export as .srt/.vtt, or burn the captions directly into the video frame.

When you'd use this

  • You need to upload a properly timed subtitle file to YouTube or Vimeo alongside your video.
  • Your video editor supports importing SRT files and you'd rather not manually time each caption line.
  • You're archiving a searchable, timestamped record of a video's spoken content for later reference.

Frequently asked questions

What is an SRT file?

A plain-text subtitle format listing cue numbers, start/end timestamps, and text — supported by nearly every video platform and editor.

Can I edit the timestamps or text before exporting?

Yes — the transcript is editable in the browser before you download the SRT file.

Does it work on audio-only files too?

Yes, though for an audio file the SRT is more useful as a transcript-with-timing than as video captions.

Which languages are supported?

The underlying Whisper model supports many languages, though accuracy is strongest for English in this browser-optimized configuration.

What's the difference between this and VTT?

SRT and VTT carry the same basic information (timed text cues); VTT adds some web-specific styling options and is what HTML5 video players expect natively, while SRT is the more universal format for editors and upload forms.

Related tools

Ad slot