Captions put the audio into text for someone who cannot hear it. Subtitles put the dialogue into another language for someone who can. The files are identical in format; what differs is the language and what gets written down. Make either one below.
How it works
Upload the video or paste a link. The text comes back in the language spoken: that is your captions track.
Correct names and terms. For captions, add notes for sounds that matter, such as [door slams].
From the download menu, translate into any of 35 languages and download an SRT per language. Those are your subtitles tracks.
The difference in practice
Usage also depends on where you are. In the UK and much of Europe "subtitles" covers all of the above. In the US and Canada the caption and subtitle distinction is kept. Platforms follow one habit or the other: YouTube says subtitles for everything, Vimeo asks you to label each track as one or the other.
Which one do you need
What the generator here produces is a transcript of the speech with timing: a captions track once reviewed, minus sound notes, which you add by hand where they matter. Formats are covered in the SRT file format and the VTT file format.
Before you rely on it
Each cue is a phrase from the transcript with its start and end time. Most run a few seconds. A passage spoken without a pause can come out as one long cue of up to about half a minute, so split those in your editor if your platform wants two short lines at a time.
From the download menu an account with credits can translate the subtitles into 35 languages and download them as SRT. Timing is kept from the original, so the translated file fits the same video.
You get the subtitle file. Fonts, colours, position and captions drawn into the picture are done in your video editor or player, which reads this file.
Open the transcript, correct a misheard name or number on its line, and the SRT and VTT you download carry the correction with the timing unchanged.
On public test recordings, about 7 words in 100 differed from the reference for clean English read speech, between 4 and 9 in 100 for Spanish, Portuguese, Russian, French and German, and about 21 in 100 for Hindi. Noisy rooms, music and crosstalk do worse. Method and every number: the benchmark.
Up to 10 hours or 5 GB per recording. The box on this page takes files up to 500 MB; larger ones continue on the upload page. 99+ languages, detected automatically.
Pricing
The preview is free. When the full transcript needs a pack, one-time packs are $4 for 500 minutes, $8 for 1,000 minutes, $12 for 2,000 minutes, $24 for 5,000 minutes. Credits never expire, which comes to about $0.29 to $0.48 per hour of audio.
| Recording | $4 or $8 pack | $12 pack | $24 pack |
|---|---|---|---|
| 5-minute video | $0.04 | $0.03 | $0.02 |
| 30-minute video | $0.24 | $0.18 | $0.14 |
| 2-hour recording | $0.96 | $0.72 | $0.58 |
Figures are the share of a pack each recording uses. A button opens secure checkout for that pack. Every export format is included; full details on the pricing page.
FAQ
Captions are for viewers who cannot hear the audio: same language as the speech, with important sounds described. Subtitles are for viewers who can hear but need a translation of the dialogue.
Not quite. Closed captions are captions the viewer can switch on and off. Subtitles usually mean a translation. In British usage the word subtitles is used for both.
Subtitles for the deaf and hard of hearing: subtitles that also include sound descriptions and speaker identification, as captions do.
No. Both are delivered as SRT, VTT and similar files. The difference is in the content and language of the text, not the format.
Captions: accurate, synchronised text in the language of the audio that includes meaningful non-speech sounds. Translated subtitles alone do not meet caption requirements.
Every page in this set uses the same upload box and the same export. All subtitle pages
Free preview. Captions in the spoken language, subtitles in 35 more; packs from $4.