Upload a Cantonese video or audio file, or paste a link, and download timed subtitles in Traditional Chinese characters: SRT for YouTube and video editors, VTT for web players.
How it works
Drop a file, or paste a public link from YouTube, Google Drive or a podcast feed. Files over 500 MB continue on the upload page, up to 10 hours or 5 GB.
Read the first Cantonese cues against the audio. Correct a line on the transcript and the subtitle file carries the correction.
SRT for YouTube Studio and video editors, VTT for web players. TXT, DOCX and JSON come from the same transcript.
What to expect with Cantonese
For a transcript rather than subtitles, see transcribe Cantonese and Cantonese YouTube video to text. For subtitles from any YouTube link, YouTube to SRT; for any file, the SRT generator.
Captioning Cantonese
Hong Kong has two ways to subtitle Cantonese. Television has long used standard written Chinese (書面語), which a Mandarin reader can follow, while online video, comedy and interviews increasingly use written Cantonese with its own characters: 嘅, 咗, 唔, 佢, 係, 冇. The text from a Cantonese recording keeps the colloquial words and particles (啦, 喎, 咩), so it reads like the speech. If your audience expects broadcast-style subtitles, that rewrite is an editorial pass you make on the transcript.
Chinese characters carry a lot of meaning each, so a cue holds far fewer characters than an English line holds letters. Dense dialogue in Cantonese can outrun what a viewer reads in the time the cue is on screen; split or shorten those cues rather than shrinking the type.
Delivery
<track> element with srclang="yue". How to attach it.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.
Cue times are taken from the recording itself, so the file lines up with the video or audio you uploaded. If you trim the start of the video afterwards, shift the cues by the same amount in your editor.
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.
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.
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.
Speakers are identified and named in the summary, key quotes and chapters. The cues in the subtitle file carry the words and their timing only.
Pricing
The preview is free. When the full transcript needs a pack, one-time packs are $6 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 $0.72 per hour of audio.
| Recording | $6 or $8 pack | $12 pack | $24 pack |
|---|---|---|---|
| 15-minute YouTube video | $0.12 | $0.09 | $0.07 |
| 1-hour sermon | $0.48 | $0.36 | $0.29 |
| 2-hour radio archive tape | $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
Upload the video or paste its link in the box on this page. The Cantonese speech is transcribed in Traditional Chinese characters; read it through, correct any line, and download SRT or VTT from the transcript.
Cantonese. The text keeps colloquial Cantonese words and particles such as 嘅, 咗 and 喎, written in traditional characters. Converting to standard written Chinese is an edit you make on the transcript.
The output is traditional characters. Converting to simplified is a separate step in a converter of your choice.
We have not published a benchmark figure for Cantonese, so we do not quote one. Judge it on your own recording: the free preview (first 20 minutes free) shows the text before you pay.
Up to 10 hours or 5 GB per file. Files over 500 MB continue on the upload page rather than in the box on this page.
Every page in this set uses the same upload box and the same export. All subtitle pages
First 20 minutes free. Cantonese SRT and VTT from one upload; packs from $6 for 500 minutes.