Transcribe long Voicy broadcasts your talks, ready to read.
A long Voicy broadcast transcribes from the audio you keep as the creator, with Japanese detected automatically, and a 60-minute talk comes back as text in about 2 minutes. The first 20 minutes are free, and eight 60-minute talks (480 minutes) fit the $6 pack of 500 minutes.
From voice to written posts
A talk that took an hour to record can feed a week of writing.
Which file to use
The simplest source is the original you recorded before it went up, which may still be on your phone or computer. If your creator tools offer a download of a past broadcast, that works too; check the format, often an audio file such as M4A or MP3. Voicy links are not read directly, so upload on upload page. If you edited the broadcast before publishing, upload the edited version so the text matches what listeners heard.
Japanese with English terms
Japanese is detected automatically, and English words dropped into Japanese speech, such as product names, business terms and loanwords, are handled. A talk that moves into English for a stretch is detected on its main language. When a guest joins, the summary, key quotes and chapters name each speaker, so an interview episode reads clearly.
A month of talks
A daily 15-minute broadcast is about 450 minutes a month and fits the $6 pack of 500. A weekly 60-minute premium talk on top of that daily show reaches about 690 minutes, which goes on the $12 pack of 2,000. Two months of the daily show alone come to about 900 minutes, also inside the $12 pack.
Uses for the text
Turn a talk into a blog article or a newsletter, quote yourself accurately on social media, or let listeners who prefer reading catch up. The brief lists the takeaways, the chapters mark each topic, and the questions the talk answered make a ready FAQ. A creator who records every weekday can turn each week's talks into one long-form post, quoting the best lines word for word.
Voice broadcasts elsewhere
Spoken ideas disappear into the archive unless someone writes them down.
✗ Audio only
Good talks that search engines and readers never see.
- Rewriting a talk from memory
- Listeners who would rather read
- OpenAI's Whisper API rejects files over 25 MB
- Quotes you cannot check
- Old episodes nobody finds
- Hours spent typing show notes
✓ Transcribed
Each talk as text you can edit and publish.
- About 2 minutes per hour
- Japanese with English terms
- Takeaways in the brief
- Chapters per topic
- Chat to find a phrase
- DOCX to edit into an article
Sample
A Voicy talk, as it comes back.
This sample is illustrative and was written for this page, not taken from a real broadcast. Timestamps follow a 60-minute talk.
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
- Unlimited AI chat per 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
- Priority queue
- All export formats
- Unlimited AI chat per transcript
Bulk pack
$24/5,000 min
83 hours of audio — $0.29 an hour. Credits never expire.
- 5,000 minutes of audio
- Priority queue
- API access for batch pipelines
- All export formats
FAQ
Voicy talks, the common questions.
How fast is a 60-minute talk transcribed?
In about 2 minutes, since processing runs at about 2 minutes per hour of audio. A long live recording of 3 hours takes around 6.
Can I paste my Voicy channel link?
No. Voicy links are not read directly, so upload the audio file instead. If a talk also went out on YouTube, that link can be pasted. A copy you placed in Google Drive can be pasted as a Drive share link, which saves uploading from a slow connection.
Does it get Japanese right with English mixed in?
Japanese is detected on its own and English terms inside Japanese speech are handled. Proper nouns and niche jargon are worth a quick read before you publish.
Could a Voicy recording be too long or too big?
Each upload can be 10 hours or 5 GB. Voice audio is small, around 30 to 60 MB an hour depending on bitrate, so a talk sits far below either limit.
What does it cost?
On a first visit, a talk up to 20 minutes is transcribed in full and a longer one is previewed. A pack from $6 then completes it from the preview's end, and leftover credits never expire.
What comes back, and is my audio kept private?
Each talk arrives with the brief, chapters and chat, and downloads as TXT, DOCX, SRT, VTT and JSON. Creator audio is transcribed on our own servers and never used for training, and WhipScribe has no integration with Voicy.
Related
More Japanese audio pages
Upload your Voicy talk. A talk of up to 20 minutes is free on your first visit.
Transcribe my Voicy broadcastOperated by Neugence Technology Pvt. Ltd. · contact@whipscribe.com · Security · Privacy · Terms