How a Chinese video becomes text
Drop in the video file without converting it: MP4, MOV, MKV, WEBM, AVI, 3GP or a screen recording from your phone. The sound is pulled out on our server, and every timestamp points to the same moment in the original video. If the video is online, use Import from link: public YouTube, TikTok and Vimeo videos, Dropbox and Google Drive share links and direct file links all work. Only the audio is fetched, one video per link, and several links can wait in the queue.
Videos on platforms that need an app or a sign-in to watch, such as WeChat Channels, are easiest to bring in as files: save the video and upload it.
Simplified, traditional and punctuation
There is no switch between simplified and traditional characters, and the draft may use either. If you need the other set, convert the exported text with a converter or with the Chinese conversion in Word. Punctuation can be thin in the draft, especially in fast speech; add commas and full stops before exporting subtitles.
Mandarin from mainland China, Taiwan, Singapore and Malaysia all transcribe well. Strong regional accents, and dialects such as Sichuanese or Hokkien, produce weaker drafts; Cantonese has its own setting. Homophones are the classic error in Chinese (的, 得, 地; 在 and 再), so scan for them with the player running.
Mandarin with English mixed in
Tech reviews, business talks and student vlogs often drop in English: PPT, deadline, project. Those words usually come out in English letters. For a video that alternates heavily between the two languages, see the Chinese-English mixed transcription page.
Chinese videos people transcribe
Typical uploads:
- University lectures and online courses, for notes.
- YouTube interviews, podcasts and documentaries, for quotes and subtitles.
- Product reviews and vlogs from creators who want Chinese captions.
- Recorded meetings and training videos.
- Family videos and interviews with grandparents abroad.
Chinese subtitles, accuracy and English
Export SRT or VTT for Chinese subtitles; they open in YouTube Studio, Premiere Pro, DaVinci Resolve, CapCut and VLC. Clear Mandarin gives a strong draft; names, numbers and homophones are what to check. Speaker labels are available on paid plans and with a Minute Pack.
The transcript is written in Chinese as it was spoken; nothing is translated. To read it in English, open the Google Translate link on the transcript, or use the AI prompt export to hand the text to ChatGPT, Claude or Gemini. For recordings without video, see the Chinese audio to text page.