Drop it in
Interviews, tutorials or a camera roll clip. Choose a file and its language.
Transcribe it, fix the words, and save the video with captions on the picture.
MP4, MOV, WebM, MKV & more · up to 1 GB
Choose several files to transcribe them one after another.
A transcript you can work with
Click a word.
Hear the moment.
Edit the text. Label the speakers.
Export subtitles that stay in sync.
Several files
Free: up to 30 minutes per file, one file at a time. With credits: up to 3 hours per file, two at a time, with speaker labels. Finished transcripts are saved in Saved transcripts on this device; keep this tab open until files finish.
This browser cannot read the duration. Enter the recording length; the processor checks it before transcription.
Free up to 30 minutes, 2 files a day. Credits add longer files (up to 3 hours), speaker labels and batches.
Live transcript
Words appear as each 30-second section finishes. The editor opens when the whole recording is done.
Transcript ready
Click a word to hear it. Choose Edit to make a correction.
Edits save on this device.
Your edits are included in every export.
Review names, numbers and speaker labels before sharing. Automatic transcripts can make mistakes.
Machine translation, included with your credits. Review it before use.
Need to know who said what? Transcribe again with speaker labels, using credits. This transcript stays in Saved transcripts.
Interviews, tutorials or a camera roll clip. Choose a file and its language.
Listen, search and fix a word. Name each speaker. Your edits save as you go.
Download captions for your video editor, or a clean transcript for your article.
Try it first with the example: choose Try an example above, then Download.
Burned-in captions are part of the picture. They show on every phone, social app and TV, and nobody has to switch them on, which suits short clips that people watch muted. They can't be turned off, restyled or translated later.
A subtitle file keeps the captions separate. Choose Subtitles (.srt) in the same menu for a video editor, YouTube or a site's caption upload, where viewers can switch them on and off. The subtitle generator has more on SRT and VTT.
Each caption is timed from the words' own timestamps: at most 6 seconds and 80 characters on screen, in no more than two balanced lines, and never two at once. Your corrections are included. Text sizes scale with the picture, so a vertical phone video and a landscape recording get the same look.
The captions are drawn in your browser, frame by frame, and the video is encoded again at its own size and frame rate. Anything wider than 1920 pixels on its long side is scaled to 1920. In an MP4 the sound is copied as it is, without re-encoding. The saved file keeps no location or camera details from the original.
Making the transcript is the only step that can use our servers. See Privacy for what is sent and how long it is kept.
Burned-in captions use the transcript's own language. A paid transcript can also be translated in the same editor and downloaded as subtitles in another language. Machine translation needs a native speaker's review before you publish.
A numbered cue has a start time, an end time and the words shown during that interval. Import the file into your video editor as a subtitle track. This written example demonstrates the export format; it is not a transcription accuracy sample.
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.
Example TXT · Example SRT · Example VTT · Example CSV
SRT uses a comma before milliseconds; WebVTT uses a dot and begins with WEBVTT. These files contain captions, not the video itself. Review cue timing against your recording.
Yes. They are drawn onto the picture, so they show everywhere the video plays, including apps that ignore subtitle files. To keep captions switchable, download Subtitles (.srt) instead and upload it with the video.
Adding the captions is free. The transcript it needs is free for recordings up to 30 minutes, with 2 free StemVocal jobs a day. Longer recordings, up to 3 hours, use credits.
MP4, MOV, WebM and MKV files up to 1 GB. The captioned video is saved as MP4 where the browser can write it, otherwise as WebM. Videos larger than 1920 pixels on the long side are saved at 1920.
No. The captions are drawn in your browser, and the captioned video never leaves your device. Making the transcript sends the recording's sound for transcription, as described in Privacy.
Choose Small, Medium or Large text; white with an outline, white on a black box, or yellow with an outline; and the top or bottom of the picture. The preview shows the look on your video before you save it.
Every frame is drawn again, so it depends on the video's length, its resolution and your device. On a computer it takes about as long as the video lasts, or less; a phone can take longer. Keep the tab open until the download starts.