Translate Chinese Video to English

What you get back

• An English transcript next to the original Chinese transcript, plus a timestamped version.
• English subtitles as SRT and VTT files.
• With Full translation output on: an English voice track in which each person (up to 8) speaks in a copy of their own voice, the translated audio as M4A, and an MP4 that keeps your original picture, music and effects.
• Chinese is detected automatically. The tool above is already set to English, so you only drop in the file.

Chinese to English at a glance

Mandarin to English expands the text — English needs more syllables for the same meaning — so the dubbed voice may speed up in dense passages. Homophone errors in the Chinese transcript can produce odd English lines; check names.

Speech recognition is tuned for Mandarin, so Mandarin recordings give the strongest results; Cantonese and other varieties are less reliable. Chinese has many homophones, so names and specialised terms in the Chinese transcript are worth checking before trusting the English.

Businesses use this direction to review supplier calls, training material and market research from China; academics use it for interviews and lectures.

Four-character idioms

Chinese speakers use chengyu, four-character set phrases with a story behind them. 画蛇添足 ("drawing legs on a snake") means spoiling something by overdoing it; 马马虎虎 ("horse horse tiger tiger") means so-so. Machine translation knows the common ones, but rarer idioms can come out word for word and sound surreal in English. Speeches, business presentations and lectures use the most chengyu, so read the English for lines that make no literal sense and check them against the Chinese transcript.

万, 亿 and Chinese counting

Chinese groups large numbers by 万 (10,000) and 亿 (100 million). 5千万 is 50 million, 3.5亿 is 350 million, and 20万 is 200,000. Conversions are where figures go wrong, especially when the speaker mixes units in one sentence ("一亿两千万"). For sales numbers, budgets and specifications, compare every figure with the Chinese transcript before you rely on the English. Currency stays in yuan (also spoken as 块) unless you add a conversion.

Names, companies and places

Chinese names have one character spelling and several possible English ones. Mainland names are written in pinyin (Zhang Wei), Taiwanese names often use older spellings (Chang Wei), and many people have an English name they prefer. Companies often have official English names that differ from a pinyin reading. Homophones make this harder: a misheard character in a name produces a different, plausible name. Check every person and company name against how they write it themselves; translating names and technical terms has a checklist.

Taiwan, Singapore and Malaysia

Speech recognition is tuned for Mandarin. Mandarin with a Taiwanese, Singaporean or Malaysian accent usually works, with more errors in local words and in speech that mixes in Hokkien, Malay or English. Cantonese and other Chinese languages are less reliable. Try a two-minute clip before a long batch.

English subtitle length

Chinese packs a lot into few characters, so the English for one cue is much longer on screen. When Mandarin is fast, English cues can be too long to read in time; splitting them in the SRT fixes that. The dub has a similar problem in reverse: English needs more syllables, so in dense passages each line may be sped up, never more than 1.15×. Each person speaks in a copy of their own voice, up to 8 people per file.

Text on screen, such as slides, product labels and the hard-coded captions common in Chinese videos, stays in Chinese; only speech is translated.

Your files only

Drop in the video file itself. Links from Douyin, Bilibili, WeChat Channels or YouTube can't be pasted, and translating someone else's content needs their permission.

Costed examples

Cost: 1,350 credits ($1.35) for the English dub, which includes the subtitles and both transcripts, or 27 credits (2.7¢) for English subtitles and transcripts without a voice.

Cost: 350 credits (35¢) for the English dub, which includes the subtitles and both transcripts, or 7 credits (0.7¢) for English subtitles and transcripts without a voice.

Cost: 2,500 credits ($2.50) for the English dub, which includes the subtitles and both transcripts, or 50 credits (5¢) for English subtitles and transcripts without a voice.

Using the tool on this page

• The spoken language is detected automatically; you select the output language — the spoken language itself for an untranslated transcript, or another language for a translation. Files can be up to 2 hours long.
• Only the audio is sent for processing — the video stays on your device — and audio and text are deleted within 30 minutes of delivery (how files are protected).
• You can download a translated video that keeps your music and effects, the translated audio as M4A, a transcript and subtitles (SRT and VTT). Every output, step and limit is explained on the video translator page.