Paste the YouTube link. The Cantonese speech is transcribed in Traditional Chinese characters, then each line is translated into English with its original timing, so the English SRT or VTT fits the video. Packs from $4 for 500 minutes; the translation adds no charge.
How it works
Paste it in the box at the top; the audio is fetched for you. If YouTube refuses the link, drop the downloaded video instead. Files up to 10 hours or 5 GB.
The free preview of the opening minutes shows the Cantonese text first, so you can judge it before you pay. Unlock it with a pack, then correct names and terms: errors in the original carry into the English.
Open the language control above the transcript, choose English under Translate into, then download SRT or VTT in English. A bilingual download carries both languages.
The short answer
People bring Hong Kong interviews, TVB-style clips, podcasts and family videos from Hong Kong and the Cantonese diaspora. For Cantonese-only subtitles see Cantonese subtitles; for the Cantonese transcript as text, Cantonese YouTube video to text.
Cantonese into English
Spoken Cantonese uses words and particles that standard written Chinese does not, and Hong Kong speech drops English words into Cantonese sentences constantly. The English words stay as said; the particles, which carry tone rather than content, mostly disappear in English.
Cantonese is transcribed as its own language, not as Mandarin, so the English is translated from what was actually said in Cantonese.
The rule that matters most: errors in the original carry into the English. Correct names and terms on the Cantonese transcript before you translate.
Delivery
srclang="en". How to attach it.Before you rely on it
An unlocked transcript translates into 99 languages from the language control above it, and each language downloads as SRT, VTT, TXT or DOCX. Timing is kept from the original, so the translated file fits the same video; translating an unlocked transcript adds no charge beyond the minutes the transcription used.
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.
Pricing
One-time packs are $4 for 500 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. The figures are the transcription of the Cantonese video; translating an unlocked transcript adds no charge beyond the minutes the transcription used.
| Recording | $4 pack | $12 pack | $24 pack |
|---|---|---|---|
| 15-minute interview | $0.12 | $0.09 | $0.07 |
| 1-hour podcast | $0.48 | $0.36 | $0.29 |
| 2-hour family video archive | $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
Paste the YouTube link in the box on this page. When the Cantonese transcript is ready, open the language control above it, choose English under Translate into, then download SRT or VTT in English. Each English line keeps the original timing.
No. Translating an unlocked transcript adds no charge beyond the minutes the transcription used. Translation needs an unlocked transcript; packs start at $4 for 500 minutes and credits never expire.
Yes. Each line is translated in place and keeps its start and end time, so the English SRT or VTT fits the same video.
Yes. The Cantonese SRT and VTT are downloads of the same transcript, and a bilingual download carries both languages.
We have not published a benchmark figure for Cantonese, so we do not quote one. Judge it on your own recording: the free preview (free preview of the opening minutes) shows the text before you pay. The English is machine translation and its quality is not measured, so have a fluent reader check anything formal.
No. Cantonese is transcribed as its own language (yue), in traditional characters, and the English is translated from that transcript.
Some videos sit behind a sign-in check and refuse automated access. Download the video, or its audio, and drop the file instead; the result is the same.
Up to 10 hours or 5 GB per file for the transcript; translation covers about 6 hours of dense speech per recording.
Every page in this set uses the same upload box and the same export. All subtitle pages
English SRT and VTT from one Cantonese transcript; packs from $4 for 500 minutes; the translation adds no charge.