Generate Cantonese subtitles for your English videos

From the Latin alphabet to Chinese characters

English is written in the Latin alphabet and Cantonese in Chinese characters, so the exported file uses a different writing system from the audio that produced it. The subtitle formats handle that — SRT and VTT are plain text and carry any script — but the font in whatever plays the file has to cover it.

This is the most common reason a Cantonese subtitle track looks correct in an editor and shows boxes or blanks on a device. Test on the target platform before you publish a batch.

How English audio becomes Cantonese subtitles

Audio in English (English) is transcribed first, then translated into Cantonese (粵語). Because the translation runs on the transcript rather than on the audio, the Cantonese subtitle file keeps the timings of the original English speech — each line appears at the moment it was actually said.

Why translate English video into Cantonese

English is spoken principally in worldwide; Cantonese in Hong Kong, Macau and Guangdong. A Cantonese subtitle track is what lets one recording reach both audiences without re-recording, re-editing or dubbing it.

Because subtitles are a separate file rather than part of the picture, you can attach several language tracks to the same video and let viewers pick.

About the English audio

English has a wider spread of accents than any other language here, and the gap between spelling and pronunciation means recognition leans on context rather than sound alone. Names and technical terms are where errors concentrate, because those are exactly the words context cannot predict.

About the Cantonese subtitles

Cantonese is a distinct spoken language from Mandarin, not an accent of it, and it has written conventions of its own for words Mandarin does not use. Select it explicitly for Hong Kong material rather than relying on Chinese.

What an English to Cantonese subtitle file looks like

Four lines of English speech, transcribed and translated, as they come out of the exported SRT. The timings are the English speaker's — translation does not move them, which is why the file drops onto the original video unchanged.

1
00:00:01,000 --> 00:00:03,240
大家早晨。

2
00:00:03,600 --> 00:00:06,120
我遲啲會分享詳情。

3
00:00:06,480 --> 00:00:09,300
請喺下面寫低你哋嘅問題。

4
00:00:09,700 --> 00:00:12,040
今日就到呢度。

What to check before publishing

• Names and places, which translation handles less reliably than ordinary prose.
• Idiom — a phrase that is natural in English may need loosening to read well in Cantonese.
• That Chinese characters renders in your player, not just in the editor you exported from.
• Timing on fast exchanges, where two speakers overlap.