Transcribe conference sessions from a South African event, every one.
To transcribe a conference recorded in South Africa, send each session as its own file or paste the Google Drive folder that holds them, and every hour of talk comes back in about 2 minutes. The first 20 minutes are free, and a $12 pack of 2,000 minutes covers a programme of up to 33 hours with nothing on subscription.
Built for a full programme
A conference is many recordings, not one. Treat it that way.
One session, one transcript
Keynotes, panels and breakaway rooms each get their own transcript, chapters and brief. A delegate asking about the Thursday afternoon panel gets that panel, not a scroll through three days of audio.
The folder link does the uploading
If the AV crew left the sessions in a shared Google Drive folder, paste the folder link and the recordings are pulled in from there. Nothing needs to be downloaded to a laptop and pushed back up over a slow venue connection.
The arithmetic for three days
Six sessions a day at about an hour each is 18 hours, or 1,080 minutes. That sits on the $12 pack of 2,000 minutes with room left for the recordings that arrive late from a second room.
Languages from the stage
A session in English, an Afrikaans panel and a Zulu address are each detected on their own. When one speaker moves between languages mid-sentence, the transcript follows the main language of that recording, so plan to check the passages in the other one.
Where conference recordings get stuck
The recordings exist. Nobody has time to listen to all of them.
✗ A folder nobody opens
Most event teams end up with gigabytes of session video and a promise to publish write-ups that never ship.
- Files named by room number and time
- A single person listening at 1x
- Uploads that fail on venue Wi-Fi
- Tools that stop at the Whisper API's 25 MB limit
- Nothing to search when a delegate asks
- Write-ups that arrive weeks after the event
✓ A searchable programme
Each recording becomes a document you can quote, link and send to the speaker for a check.
- Paste the Drive folder once
- Each hour of a session back in about 2 minutes
- Chapters that match the talk's own sections
- Names, figures and dates pulled from each talk
- Chat that answers questions about one session
- Exports for captions and for the conference report
Sample
A panel session, as the transcript reads.
This excerpt is illustrative, written for this page rather than taken from a real event. It shows how timestamps and speaker turns sit in a conference panel recording.
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
Conference recordings from South Africa, answered.
How long until every session of the conference is text?
Each hour of a session takes about 2 minutes. A one-hour keynote is back in a couple of minutes, and an 18-hour programme adds up to about 36 minutes of processing in total. The public measurements are on the long-files proof page: 9.31 hours of audio finished in 1,033 seconds.
What does a three-day conference cost?
Eighteen hours of sessions is 1,080 minutes, which fits the $12 pack of 2,000 minutes, about $0.36 per hour. A one-day event of up to eight hours fits the $6 pack of 500 minutes. Packs are sold in US dollars, the minutes never lapse, and the first 20 minutes are free so you can check one session first.
Should I split a full day into sessions?
Yes, when the room recorded continuously. One file can run to 10 hours or 5 GB, so a full day uploads whole, but one session per file gives each talk its own brief and chapters. Before the first pack, uploads go up to 2 GB; a larger day file starts once a pack is on the account.
Which South African languages are recognised?
English, Afrikaans and Zulu are among the 99 languages detected automatically, with no setting to choose. A session that switches between languages is transcribed on its main language, so a short passage in a second language deserves a read before you publish a quote from it.
Can I get transcripts from a Google Drive folder?
Paste a Drive share link to a single recording or to the whole folder, and the files are fetched directly. Recordings kept on Facebook or Teams need to be downloaded first and then uploaded.
Which formats come back, and who sees the sessions?
TXT, DOCX, SRT, VTT and JSON come out of every session. SRT and VTT fit the video you publish afterwards, and DOCX suits the event report. Recordings are transcribed on our own servers and are never used for training, which matters when a closed session was recorded too.
Related
More for event teams
Send the first session. Read 20 minutes of it free.
Transcribe conference sessionsOperated by Neugence Technology Pvt. Ltd. · contact@whipscribe.com · Security · Privacy · Terms