How do you reduce a video's size for upload? Keep the sound, shrink or drop the picture.
For a transcript, drop the picture: ffmpeg -i video.mp4 -vn -ac 1 -c:a aac -b:a 64k audio.m4a turns a 5-hour 1080p video of about 18 GB into roughly 144 MB in a minute or two. If you also need a watchable copy, re-encode to 720p (about 0.9 GB an hour at 2 Mbps) in HandBrake or ffmpeg; either way the 5 hours are transcribed in about 10 minutes.
Three sizes for the same recording
The transcript is made from the sound. How much picture you keep is up to you.
Audio only, the smallest
Mono AAC at 64 kbps uses about 29 MB per hour and keeps speech clear. A whole 10-hour day comes to about 290 MB, under the 500 MB this page's box accepts. The extraction takes about as long as reading the file once, a minute or two for most recordings.
720p, a watchable copy
ffmpeg -i video.mp4 -vf scale=-2:720 -c:v libx264 -b:v 2M -c:a aac -b:a 96k smaller.mp4, or a 720p preset in HandBrake (preset names change between releases). At about 2 Mbps an hour is near 0.9 GB, so up to around five hours fits in 5 GB. Encoding can take as long as the video runs.
480p, smaller still
Changing 720 to 480 and 2M to 1M halves the size again to roughly 450 MB an hour. Slides and faces are still readable for reference, and the sound, which is all the transcript uses, is untouched.
Where it goes next
Up to 500 MB, drop it in the box above. Larger files carry on at the upload page, which takes up to 10 hours or 5 GB per file. A file can be up to 5 GB with or without a pack; a bigger one can be split or exported as audio.
Shrinking the wrong way
Most size problems get fixed by throwing away quality the transcript needed.
✗ Crushing the whole video
Squeezing every setting to the bottom makes a small file nobody can use.
- Audio at 16 kbps, voices smeared
- A re-encode running all night
- Picture kept, speech damaged
- Cut into clips to dodge a limit
- Several transcripts for one talk
- Still over 5 GB after all that
✓ Shrinking with intent
Keep the speech intact; reduce only what the transcript ignores.
- Speech kept at 64 kbps or more
- Audio out in a minute or two
- A 720p copy only if you need one
- One file, one timeline
- About 10 minutes for 5 hours
- Packs from $4 for 300 minutes
Sample
A five-hour training video, reduced to audio first.
Illustrative lines written for this page; not a real course. Timestamps match the original video.
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 $4 (300 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
$4/300 min
5 hours of audio — $0.80 an hour. One-time — credits never expire.
- 300 minutes of audio
- All export formats
- AI chat over the whole transcript
- Executive summary & key quote
Best value
$18/3,000 min
50 hours of audio — $0.36 an hour. Credits never expire.
- 3,000 minutes of audio
- Summary, chapters and key quotes
- All export formats
- AI chat over the whole transcript
Bulk pack
$32/6,000 min
100 hours of audio — $0.32 an hour. Credits never expire.
- 6,000 minutes of audio
- Summary, chapters and key quotes
- API access for batch pipelines
- All export formats
FAQ
Reducing video size, answered.
Do I need to shrink it at all?
Only if it is over 5 GB or longer than 10 hours. Most files upload as they are, up to 10 hours or 5 GB, and an MP4 of a few gigabytes can go up unchanged through the main upload page.
Which option keeps the best transcript?
Audio only. The transcript comes from the sound, and the audio route leaves it at a speech-friendly bitrate while removing everything else. Lowering video resolution does not change the words at all.
How big is my video now?
Rough guide: 1080p at 8 Mbps is about 3.6 GB an hour, 720p at 2 Mbps about 0.9 GB, 480p at 1 Mbps about 450 MB. Phone 4K can be over 10 GB an hour. Check the real size in Finder, File Explorer or the Files app.
What does a long video cost to transcribe?
Minutes are counted from the audio length, not the file size. Packs start at $4 for 300 minutes, and credits never expire. The opening minutes are a free preview.
Is the video already on YouTube, Vimeo or Drive?
Then skip shrinking and paste the link: YouTube, Vimeo, Google Drive share links, Twitch and Kick VODs and podcast feeds need no upload at all.
Languages, exports and privacy?
99 languages are detected automatically. Exports: TXT, DOCX, SRT, VTT and JSON. Recordings are transcribed on our own servers and are never used for training.
Related
Related pages
Make it smaller, keep every word. The opening minutes of the video are free.
Transcribe my videoOperated by Neugence Technology Pvt. Ltd. · contact@whipscribe.com · Security · Privacy · Terms