Transcribe a Mandarin podcast and publish the episode as text too.
A 90-minute Mandarin podcast episode recorded in Australia comes back as Chinese text in about 3 minutes, and Mandarin is detected automatically, including the English words hosts drop in. The first 20 minutes are free; a 20-episode season of 90 minutes, 1,800 minutes, fits the $12 pack of 2,000.
For the producer behind the mic
Listeners search in Chinese. A transcript gives every episode words they can find.
Show notes that write themselves
Chapters with timestamps and a brief of the episode's argument are a ready draft for the episode page, the newsletter and the post on Xiaohongshu or Instagram.
The feed, not the files
Paste the show's RSS feed or one episode link and the audio is fetched, so a producer can work through the back catalogue without downloading anything.
Captions for the video cut
If the episode also goes to YouTube or Bilibili, the SRT and VTT exports give Chinese subtitles timed to the speech.
Quotes for the trailer
Key quotes are pulled out with their timestamps, so the strongest 30 seconds for a clip can be found without scrubbing through the edit.
Why episodes stay invisible
An hour of good conversation in Mandarin is audio only, and search engines cannot hear it.
✗ Audio only
The episode goes out, the show notes are three lines, and the best moments are buried somewhere after minute forty. For a show made by two friends in Sydney or Melbourne on weekends, there is rarely time left after editing to write anything at all.
- Show notes written from memory
- No text for listeners who prefer reading
- Clip hunting by scrubbing the timeline
- Subtitles skipped on the video version
- A back catalogue nobody can search
- A subscription tool for a weekly show
✓ Audio plus text
Every episode carries a full Chinese transcript and chapters. The producer pastes the chapters into the episode page, picks two quotes for social posts and sends the full text to the guest the same day.
- About 3 minutes per 90-minute episode
- Chapters ready for the episode page
- Hosts and guests named in the summary
- Key quotes with timestamps
- SRT and VTT for the video upload
- Credits that never expire
Sample output
A Mandarin interview episode, as the transcript reads.
Illustrative lines written for this page; no real show, host or guest. In English: welcome back to the show; today's guest moved from Shanghai to Sydney ten years ago; you said starting a business here was harder than you thought; the first year we basically had no customers.
Export
One transcript. Five clean formats.
Every pack exports all five — no format is held back for a higher tier.
Plain text
De-ummed paragraphs. Ready to paste.
SRT captions
Timed to the speech. Every video editor reads this.
WebVTT
HTML5 player + YouTube uploads.
Show notes
Formatted with chapters and pull-quotes.
Machine-readable
Timestamped text for your own tools.
Pricing
Honest pricing, no surprises.
A pack from $6 (500 minutes) opens the full transcript. After that, no subscription and no auto-renew — every tier is a one-time minute pack, and credits never expire. Buy once, use the minutes whenever you need them.
Casual pack
$6/500 min
8 hours of audio — $0.72 an hour. One-time — credits never expire.
- 500 minutes of audio
- All export formats
- AI chat over the whole transcript
- Executive summary & key quote
Best value
$12/2,000 min
33 hours of audio — $0.36 an hour. Credits never expire.
- 2,000 minutes of audio
- Summary, chapters and key quotes
- All export formats
- AI chat over the whole transcript
Bulk pack
$24/5,000 min
83 hours of audio — $0.29 an hour. Credits never expire.
- 5,000 minutes of audio
- Summary, chapters and key quotes
- API access for batch pipelines
- All export formats
FAQ
Mandarin podcasts, answered.
Can you take episodes from our RSS feed?
Yes. Paste the feed or an episode link and the audio is fetched. Podcast and RSS links need no upload, and neither do YouTube or Vimeo versions of the show. Episodes hosted on a platform without a supported link can be downloaded as MP3 and uploaded instead.
What does a season cost?
Twenty 90-minute episodes are 1,800 minutes on the $12 pack of 2,000. A short run of five 90-minute episodes, 450 minutes, fits the $6 pack of 500. A back catalogue of fifty such episodes, 4,500 minutes, fits the $24 pack of 5,000.
How fast is it?
About 2 minutes per hour of audio, so a 90-minute episode is ready in roughly 3 minutes and a two-hour interview in about 4. A batch of ten back episodes pasted one after another finishes in well under an hour.
Our hosts switch to English mid-sentence. Is that kept?
Yes. The episode is detected on its main language, Mandarin, and English words and sentences inside it are handled in the same transcript. Intro music and stings are not transcribed; the conversation is.
The raw WAV of a long recording session is large. Will it upload?
A 16-bit 48 kHz stereo WAV uses about 691 MB an hour, so a three-hour session is around 2.07 GB, just over the 2 GB allowed before the first pack; it starts once a pack is on the account. Any file may run to 10 hours or 5 GB, and an exported MP3 is far smaller.
Who owns the transcript?
You do. Episodes are transcribed on our own servers and are never used for training. Exports come as TXT, DOCX, SRT, VTT and JSON, ready for the website, the subtitle editor or a script.
Related
More for podcast producers.
Paste your feed. The first 20 minutes of an episode are free.
Transcribe an episodeOperated by Neugence Technology Pvt. Ltd. · contact@whipscribe.com · Security · Privacy · Terms