Generate English subtitles for your Vietnamese videos

From Latin with tone diacritics to the Latin alphabet

Vietnamese is written in Latin with tone diacritics and English in the Latin alphabet, 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 English 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 Vietnamese audio becomes English subtitles

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

Tone in the Vietnamese audio

Vietnamese uses tone to distinguish words that are otherwise identical, so recognition depends on pitch as well as on the sounds themselves. Background music is unusually costly here — it competes with exactly the cue the recogniser needs.

Where tone was misheard, the English translation follows the wrong word rather than producing obvious nonsense, so errors read as plausible. A pass over the transcript before translating is worth more on Vietnamese than on most languages.

Why translate Vietnamese video into English

Vietnamese is spoken principally in Vietnam; English in worldwide. A English 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 Vietnamese audio

Vietnamese uses the Latin alphabet with a dense set of tone and vowel diacritics, and those marks are not decorative — dropping them changes the word. The transcript keeps them, so check that whatever you load the subtitle file into handles the full character set.

About the English subtitles

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.

What a Vietnamese to English subtitle file looks like

Four lines of Vietnamese speech, transcribed and translated, as they come out of the exported SRT. The timings are the Vietnamese 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
Let's start with the first question.

2
00:00:03,600 --> 00:00:06,120
Please write your questions below.

3
00:00:06,480 --> 00:00:09,300
That's all for today.

4
00:00:09,700 --> 00:00:12,040
See you next time.

What to check before publishing

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