Subtitle Generator

Subtitles in three steps

1. Choose a video, or an audio file, and pick its spoken language, or let StemVocal detect it.
2. Play it back with the captions over the picture. Click any word to hear that moment again, and correct names, numbers and anything misheard.
3. Download SRT subtitles, already selected, or switch to VTT captions.

Free subtitles cover recordings up to 30 minutes. For a longer film, lecture or livestream recording, credits handle files up to 3 hours and can add speaker labels.

Timed for reading

Subtitles should be readable at the speed people speak. StemVocal times each cue from the words' own timestamps rather than from fixed blocks. A cue stays on screen for at most 6 seconds and holds at most 80 characters, and anything longer than 42 characters splits into two balanced lines. Cues never overlap, so a player never stacks two captions at once.

Your edits come with you. When you rewrite a sentence, its words are spread across the time the original speech took.

SRT or VTT?

Choose SRT for a video editor or a site's subtitle upload form. Choose VTT for a web player that reads WebVTT captions. Both files hold the same cues and text; neither changes the video itself. What is an SRT file and what is a VTT file explain how each one is laid out and how to fix common problems. To put the captions on the picture instead, choose Video: see add subtitles to video. For a written transcript, open video to text and download Word or plain text.

Subtitles in another language

A paid transcript can be translated with the export menu still on SRT or VTT. The translation keeps each passage's original time interval; translated wording may split into different cues. Make corrections before choosing Translate, because later edits do not update an existing translation. Translation runs from English into 15 languages, or from any of them into English. It is machine translation: have a speaker of the language review it before you publish.

Already have a subtitle file? The subtitle translator translates an SRT or VTT file directly, with each cue's number, timing and formatting kept.

Adjust subtitle timing

Already have an SRT or VTT file? If every caption is early or late by the same amount, shift its timing below. For a video with a new 1.5-second introduction, move the captions Later by 1.5 seconds. The tool creates a separate subtitle file; it does not edit your video.

A fixed offset preserves cue durations and any overlaps. It also moves WebVTT inline timestamps, keeping their position within each cue. Numbers, text, styling and position settings remain in the file. Downloads are UTF-8 in the original subtitle format.

The whole file must have valid, ordered cue times. A change that would move a cue before zero is refused, so nothing is silently removed or shortened. Streaming VTT files with timestamp maps need a video editor. The limits are 20,000 cues, a one-hour offset and output times below 100 hours.

If the gap grows throughout the video, or you removed a section in the middle, one fixed shift will not fix it. Edit against the final recording or generate subtitles from that cut. Check both the beginning and the end before publishing.

Format references: W3C WebVTT cue timings and inline timestamps, and the Library of Congress SRT format description. Checked October 1, 2026.

Check before you publish

Watch the whole video with captions on, full screen included, before you upload the file. Pay attention to names, numbers and places where people talk over each other, where the transcript usually keeps one voice. Every correction you make in the editor is in the next download.

1
00:00:00,000 --> 00:00:04,000
What should we check before publishing?

2
00:00:04,000 --> 00:00:10,000
Check names and numbers
against the recording. Then save

3
00:00:10,000 --> 00:00:12,000
the corrected transcript.