Cantonese interviews, transcribed properly
Cantonese (廣東話): Cantonese is supported as its own language (yue) — distinct from Mandarin — with traditional-script output. Colloquial Cantonese particles (啦, 喎, 咩) appear in the output. Accuracy trails Mandarin; broadcast speech does noticeably better than street conversation, so plan a review pass for anything critical.
Interviews in particular: Word timestamps let you cite the exact moment an answer was given. Verbatim quotes for articles and papers, or a clean Q&A ready to code in NVivo or ATLAS.ti.
How it works
Record well
Record each voice clearly — an external mic or per-speaker tracks give the cleanest transcript.
Upload it
Drop the file into Whipscribe or paste a link. Every recording starts with a free preview of its opening minutes; a pack from $4 (300 minutes) transcribes the rest and opens every export.
Read & export
Timestamped Cantonese text in minutes. Export TXT, SRT, VTT, or DOCX.
Typical uses: Hong Kong sermons, radio archives, family-history tape.
Getting a Cantonese interview in, and quotes out
- Upload the recorder or call file (MP3, M4A, WAV and the other common formats), or paste a Google Drive link to it shared as 'Anyone with the link'.
- Speakers are identified and named in the summary, key quotes and chapters. Every transcript line carries its timestamp, so a quote can be checked against the audio before it goes into print or a paper.
- Download DOCX for coding in NVivo or ATLAS.ti (both import Word documents), TXT for notes, or SRT if the interview is published as video.
Writing Cantonese: Cantonese is written in Traditional Chinese characters in Hong Kong and Macau; colloquial written Cantonese uses characters such as 嘅, 咗 and 喺 that Standard Written Chinese does not; it is used in Hong Kong, Macau, Guangdong and the Cantonese-speaking diaspora.
Next: Cantonese subtitles · research interview transcription · a whole set of interviews · Google Drive links · pricing
Frequently asked
Can Whipscribe transcribe Cantonese interviews?
Yes. Cantonese is supported as its own language (yue) — distinct from Mandarin — with traditional-script output. Colloquial Cantonese particles (啦, 喎, 咩) appear in the output. Accuracy trails Mandarin; broadcast speech does noticeably better than street conversation, so plan a review pass for anything critical.
How are speakers handled in interviews?
Speakers are identified and named in the summary, key quotes and chapters. Word timestamps let you cite the exact moment an answer was given.
Can I code a Cantonese interview transcript in NVivo or ATLAS.ti?
Yes. Download the transcript as DOCX or TXT and import it; both programs take Word and plain-text documents. The text stays in Cantonese, the language of the interview.
How long can a Cantonese subtitle line be?
Lines written in Chinese, Japanese or Korean characters are cut at 18 characters, two lines a cue, against about 42 for Latin-script text. Delivery specs can be tighter: Netflix's Simplified Chinese timed-text guide allows 16 characters a line. Re-break lines in your subtitle editor if you deliver to a stricter spec.
How much does it cost?
Every recording starts with a free preview of its opening minutes; a pack from $4 (300 minutes) transcribes the rest and opens every export. One-time credit packs: $4 for 300 minutes, $18 for 3,000 minutes, $32 for 6,000 minutes, and credits never expire.
Is my recording private?
Yes. Recordings are transcribed on our own servers and are never used for training. Always get participants' consent before recording.