Chinese (Mandarin) tutorials and screencasts, transcribed properly
Chinese (Mandarin) (中文（普通话）): Simplified-script output by default, with sentence segmentation despite no spaces in the script. Tone-dependent homophones resolve from context. Mandarin is the model's training target; for Cantonese use our dedicated Cantonese page.
Tutorials in particular: Step-by-step narration becomes searchable text mapped to the minute it happens on screen. Written guides from spoken walkthroughs, captions for the video, searchable help content.
How it works
Record well
The screen-recording audio track is enough; a decent mic is the whole production upgrade.
Upload it
Drop the file into Whipscribe or paste a link. 30 minutes free daily, no signup to try.
Read & export
Speaker-labeled, timestamped Chinese (Mandarin) text in minutes. Export TXT, SRT, VTT, or DOCX.
Typical uses: Meetings, lectures, podcast archives, drama clipping.
Frequently asked
Can Whisper transcribe Chinese (Mandarin) tutorials and screencasts?
Yes. Simplified-script output by default, with sentence segmentation despite no spaces in the script. Tone-dependent homophones resolve from context. Mandarin is the model's training target; for Cantonese use our dedicated Cantonese page.
How are speakers handled in a tutorial?
Step-by-step narration becomes searchable text mapped to the minute it happens on screen.
How much does it cost?
About 3.3¢ per audio minute (~$2 an hour), 30 minutes free every day, no signup to try.
Is my recording private?
Yes — private infrastructure, never sent to a third-party AI service, no training on uploads. Always get participants' consent before recording.