Generate SRT subtitles automatically
Choose an audio or video file and get a timecoded subtitle file (SRT). With a video you can play it back with the captions overlaid, and you can correct the wording on screen before exporting, so it is ready to drop straight into a video editor.
If you know the speaker count, setting it greatly improves accuracy
Using the subtitles you generate
SRT is the most widely supported subtitle format — YouTube, Premiere Pro, DaVinci Resolve and VLC all read it directly. Give the exported file the same name as your video and put it in the same folder, and most players will pick it up as a subtitle track automatically.
Auto-generated subtitles are rarely ready as-is. Proper nouns, punctuation placement and line length can all be corrected on screen before export. The replace function lets you fix a recurring mis-transcription in one pass. If you loaded a video, play it back with the captions overlaid to check readability and timing.
Frequently asked questions
Can I export in formats other than SRT?
Plain text (TXT) is also available. TXT contains the body text without timecodes, which suits minutes and transcripts.
Can subtitles be split by speaker?
With speaker separation enabled, each line records who was speaking. You can rename speakers and reassign individual lines on screen.
Can I fix subtitle timing if it drifts?
Yes. Click a line's time, or choose "Edit times" from the "⋮" menu, to retype its start and end in seconds (down to hundredths). You can also add or delete lines, so you can insert speech the model skipped or remove a spurious line from a silent stretch before exporting.
Which languages can I generate subtitles in?
Eleven languages can be selected — including English, Japanese, Chinese, Korean and Spanish — plus automatic detection. The bundled model is multilingual, so languages outside the list often work via auto-detect.
Getting the audio ready, and after transcribing
Help us improve the service
Sending us the circumstances of a run — successful or failed — helps us track down problems (a failure rate needs both). Knowing which devices and settings fail most often lets us revise the recommended defaults and fix the bugs behind them. If you don't mind, leaving this on is a real help.
What is sent
Your device specs (GPU model, memory, core count), browser and OS, the model and language you chose, how far the run got, the error details, the file's format with a rough size and length, and how long it took.
What is never sent
Audio, transcripts, file names, and IP addresses. The data goes only to this site's own server, never to a third-party service.