Transcribe a long Google Pixel camera recording from the phone or a Drive link.
A 3-hour recording from a Google Pixel camera comes back as text in about 6 minutes, whether you upload the MP4 or paste a Google Drive link to it. The first 20 minutes are free, the 180 minutes fit the $6 pack of 500 minutes, and a file can be up to 10 hours or 5 GB.
From the Pixel to the text
The video may already be in the cloud. The quickest route depends on where it sits.
On the phone
The Pixel camera saves video as MP4 in the Camera folder under DCIM, and Google Photos shows it. From the phone's browser, tap the upload box here and pick the video; on a computer, copy it off over USB first.
In Google Photos only
If the phone backed the video up and then freed space, download it from Google Photos to a computer and upload it here. A Google Photos share link is not one we fetch, so save the file or move it into Google Drive.
Pasting a Drive link
Put the MP4 in Google Drive, set sharing to anyone with the link, and paste the link in the box. We fetch the file on our side, so nothing goes up from your phone, and a whole Drive folder of recordings can be pasted the same way.
What the recording becomes
Three hours of conversation returns with a brief, chapters with timestamps, key quotes and the names, numbers and dates mentioned. The people in it are named in the summary, quotes and chapters, which makes a long family or research interview easy to search.
Long Pixel video elsewhere
A three-hour phone video is easy to record and awkward to hand to most tools.
✗ Common snags
Most of them come from size, not sound.
- Whisper API uploads capped at 25 MB
- A three-hour limit or less on free tiers
- Share links from Photos that tools cannot open
- Phone uploads that stall on mobile data
- Converting MP4 to audio before every upload
- Interviews read in separate pieces
✓ Here
Upload the MP4 or hand over a Drive link.
- Pixel MP4 accepted as saved
- Drive links and folders fetched for you
- Three hours read in about 6 minutes
- Every relative named in summary and quotes
- 20 opening minutes free, first visit
- $6 covers the 180 minutes
Sample
A long interview filmed on a phone at a kitchen table, as it comes back.
This sample is illustrative and was written for this page, not taken from a real family. The timestamps show a 3-hour interview.
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
Google Pixel camera recordings, the common questions.
How long does a 3-hour Pixel recording take?
Around 6 minutes, at about 2 minutes per audio hour. The proof page lists a 2.48-hour file that finished in 200 seconds.
What does three hours cost?
On a first visit the opening 20 minutes are free. The 180 minutes fit the $6 pack of 500 minutes with 320 to spare. Ten interviews of that length, 1,800 minutes, fit the $12 pack of 2,000.
How large can the video be?
Up to 5 GB or 10 hours per file, and up to 2 GB before a pack is on the account. If the MP4 is bigger, export the audio alone, which is a few hundred megabytes at most for hours of speech.
Should I split the video?
There is no need below 10 hours. If the phone stopped and started again, upload each clip on its own, or join them in an editor for a single timeline.
What languages does it handle?
99, detected from the speech without a setting. A relative who drifts between languages is transcribed on the recording's main one, and English with Tagalog is handled in one file.
Which exports are there, and who hears it?
Five downloads: TXT, DOCX, SRT, VTT and JSON. Your audio stays on our own servers for transcription and never trains a model; delete the file and its transcript goes with it.
Related
Other phones and Drive links
Send the Pixel recording. Start with 20 minutes at no charge.
Transcribe my Pixel videoOperated by Neugence Technology Pvt. Ltd. · contact@whipscribe.com · Security · Privacy · Terms