Transcribe a long Sony XAVC S file the panel, not the gigabytes.
A two-hour XAVC S recording is 120 minutes of speech: it transcribes in about 4 minutes and fits the $6 pack (500 minutes), and the first 20 minutes are free. XAVC S is an MP4 that runs about 22 to 45 GB an hour at 50 to 100 Mbps, so a short clip uploads as it is and a long one goes up as extracted audio, about 58 MB an hour as MP3.
XAVC S, by the numbers
An ordinary MP4 on the outside, a very high bitrate inside. That decides how it reaches the upload.
Which cameras write it
XAVC S is the consumer and prosumer recording format on many Sony cameras and camcorders, from mirrorless bodies to handycams. Conferences, lectures, church services, panels and family events filmed on one are what produce long XAVC S files.
Size per hour, worked out
At 50 Mbps an hour is 50 million bits a second times 3,600 seconds, divided by 8: about 22.5 GB. At 100 Mbps it is about 45 GB. That means a 5 GB file holds roughly 13 minutes at 50 Mbps and under 7 minutes at 100, so for a long recording the sound is what goes up.
Sending the sound
XAVC S keeps its audio in the same MP4, often as uncompressed PCM. ffmpeg -i C0001.MP4 -vn -b:a 128k talk.mp3 pulls it out at about 58 MB an hour. A short clip under 5 GB can go up as it is, from this page if under 500 MB, or from the upload page if larger. If the upload refuses a file, convert to MP3 or MP4 with ffmpeg or VLC.
Clips the camera split
Some cameras and cards split long recordings into several clips. Extract the audio from each, join them in order with ffmpeg, and upload one file of 10 hours or less, so the whole event has one transcript and one clock.
Event footage, as usual
One camera on a tripod for a full day produces more data than anyone wants to move.
✗ Too big to send
XAVC S at full bitrate fills cards fast, and long files strain every upload.
- Files of tens of gigabytes
- Uploads that fail near the end
- A day split into many clips
- Re-encoding the video just to send it
- Watching back for the quote you need
- Captions rebuilt by hand
✓ A few megabytes of sound
Pull the audio, upload once, read the event in minutes.
- Two hours in about 4 minutes
- Chapters at each change of topic
- Names and dates listed
- SRT and VTT for the video
- A chat over the whole event
- Credits kept for the next one
Sample
A recorded panel, midway through the afternoon.
An illustration written for this page; no real event or panellists. Times follow the joined audio.
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
Long XAVC S files: answers
Does the upload accept XAVC S?
An XAVC S file is an MP4, so a clip under 5 GB usually uploads as it is. If the upload refuses it, convert to MP3 or MP4 with ffmpeg or VLC, or extract the audio, which is the better route for anything long.
How big is the extracted audio?
As MP3 at 128 kbps, about 58 MB an hour, so ten hours is about 576 MB. Up to 500 MB goes in the box on this page, and a larger file continues on the main upload page. The original PCM track, if you keep it as WAV, is about 691 MB an hour.
How long does a two-hour panel take?
About 4 minutes, at about 2 minutes per audio hour. A public run of 9.31 hours took 1,033 seconds.
What does a three-day conference cost?
Seven hours a day for three days is 21 hours, or 1,260 minutes, on the $12 pack (2,000 minutes) with 740 left. One 2-hour panel is 120 minutes on the $6 pack.
The event ran more than 10 hours.
Upload it as two files, for example morning and afternoon. Before the first pack, uploads go up to 2 GB; a larger file starts once a pack is on the account.
Languages, exports and privacy?
99 languages, detected automatically. Applause and music are not transcribed; speech is. Exports are TXT, DOCX, SRT, VTT and JSON. Recordings are transcribed on our own servers and are never used for training.
Related
Other camera formats
A long XAVC S recording. The event as text in minutes.
Transcribe my recordingOperated by Neugence Technology Pvt. Ltd. · contact@whipscribe.com · Security · Privacy · Terms