Transcribe Sony FX6 interviews a paper edit for the whole documentary.
A 75-minute interview shot on a Sony FX6 comes back as text in about 2.5 minutes when you upload an audio export instead of the camera files, which run to tens of gigabytes per hour. The first 20 minutes are free; a documentary of thirty such interviews is 2,250 minutes, which fits the $24 pack of 5,000.
Cinema camera to paper edit
On an FX6 shoot the sound is usually the cleanest thing on the card. That is all a transcript needs.
Four channels, one mix
The FX6 takes XLR inputs and can record several audio channels, so a typical interview has a boom on one track and a lav on another. Export a mono or stereo mix of the best channels as MP3 or WAV; a 75-minute interview is far under 500 MB as MP3 and goes straight into this page's box.
Why not the clip itself
XAVC files at cinema bitrates fill several gigabytes in minutes, so a full interview is far beyond the 5 GB a file can be. If proxies were recorded, they carry the same sound and may be light enough to upload as they are; check their size against the 2 GB limit that applies before the first pack.
The whole film, costed
One 75-minute interview is inside the $6 pack of 500. Thirty interviews, 2,250 minutes, fit the $24 pack of 5,000 with room for b-roll conversations and pickups. Credits never expire, so the second shooting block uses what the first left over.
What the edit room gets
Every interview returns with a brief, chapters with timestamps, key quotes, and the names, places and dates the subject mentions. The interviewer and subject are named in the summary, quotes and chapters. Download DOCX for the producer's notes, or JSON when your tools read timestamps from data.
Interview-heavy productions
Forty hours of interviews, one editor, and a cut due in three weeks.
✗ Logging by hand
Scrubbing every interview for the line you remember.
- Camera files dozens of gigabytes each
- Interviews logged in a spreadsheet by ear
- Typed transcripts arriving a week later
- Quotes that do not match the timecode
- Names and dates checked one by one
- Selects built from memory
✓ A paper edit in an afternoon
Every interview as searchable text.
- About 2.5 minutes per 75-minute interview
- Chapters and key quotes, timestamped
- Names and places listed per interview
- DOCX for the producer, JSON for tools
- Chat across a long interview
- A whole film on the $24 pack
Sample
A documentary interview from an FX6 shoot, as it reads back.
Illustrative only: composed for this page, not from a real production. Timestamps fall within one 75-minute 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
- 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
Sony FX6 interviews: common questions.
How long does a 75-minute FX6 interview take?
About 2.5 minutes; the work runs at roughly 2 minutes per hour of audio. A full shoot day of five hours, uploaded interview by interview, is done in about 10 minutes.
Will the timestamps match my timeline?
They match the file you upload. If you export each interview from its start, the transcript's 00:00:00 is the interview's first frame, so quotes map straight back to the clip.
Which audio channel should I export?
Whichever is cleanest, usually the lav for the subject. If the interviewer is only on the boom, mix both into one track so their questions are transcribed too.
What does a full documentary cost?
Thirty 75-minute interviews, 2,250 minutes, fit the $24 pack of 5,000. A shorter project with twelve interviews, 900 minutes, fits the $12 pack of 2,000. Packs are one-time, with no subscription.
Can I send interviews in another language?
Yes. 99 languages are detected automatically, and English words inside another language are handled. An interview that changes language partway is detected on its main language.
Which exports come back, and are the rushes private?
TXT, DOCX, SRT, VTT and JSON. Recordings are transcribed on our own servers and are never used for training, and nothing ties WhipScribe to the camera or your editing software.
Related
Cinema cameras and interview pages
Export the interview audio and upload it. Your first 20 minutes are free.
Transcribe my FX6 interviewOperated by Neugence Technology Pvt. Ltd. · contact@whipscribe.com · Security · Privacy · Terms