Drop a file
Use a recording or an SRT or VTT you already have.
Runs in this browser · Nothing uploaded · 7-week trial
Subtitle generator.
SRT and VTT.
Drop a recording or an existing subtitle file. Short cues, an editor for text and timing, then SRT or VTT download.
Runs in this browser. The file never leaves this device.
Subtitles without uploading the video
The same local transcription as Audio to text, then cues sized for on-screen reading. Import SRT or VTT to rebreak lines without spending a free transcription run.
Fifteen minutes in the browser
Short clip tools cap at a minute. Here you can work with a recording up to 15 minutes and 80 MB, the same trial limits as the other transcribe tools.
Edit text and timing before you export
Each cue has editable text, start and end times, plus split, merge and find and replace. Nudge timing in the preview until the line matches the voice.
SRT and VTT only, no burn-in
Download SRT for editors and YouTube, or VTT for HTML5 players. This page does not burn subtitles into the video file.
Who is speaking?
Speaker changes start a new cue. Names stay out of the subtitle text unless you turn on Show names in export.
Swiss German transcription
Swiss German is transcribed as Standard German like the other browser tools. Adjust wording in the editor if you need dialect spelling.
How to create subtitles
Pick the language
Choose the spoken language for new transcriptions.
Review cues
Edit text, split long lines and nudge timing in the preview.
Export
Download SRT or VTT, or copy plain text without timestamps.
Before you start
Is my video uploaded?
No. Transcription and editing stay in this tab. After the model is cached you can confirm in the Network tab that nothing is posted.
How long can the recording be?
Up to 15 minutes and 80 MB, the same limits as Audio to text.
What is the difference between SRT and VTT?
SRT uses a comma in timestamps and is common in YouTube and editors. VTT adds a WEBVTT header and uses a dot in timestamps for HTML5 video and browsers.
Can I edit text and timing?
Yes. Each cue has editable text and start and end times, with split, merge and find and replace.
Which languages are supported?
German, English, French and Italian are listed explicitly. Whisper supports more; pick the spoken language before transcribing.
Can I rebreak an existing SRT?
Yes. Drop an SRT or VTT file. The tool parses it locally and rebuilds cues. That path does not download the speech model and does not use a free run.
Does this burn subtitles into the video?
No. You download SRT or VTT and load them in your player or editor.
Why are some times inaccurate?
Whisper gives times per phrase, not per word. The tool splits duration by character count until you adjust timing in the editor.
Need longer meetings on the machine?
Vemoir for Mac captures calls locally and keeps a library without uploading files.