Transcribe long interviews shot on a Blackmagic Pocket from the audio, not the raw clip.
Blackmagic Pocket Cinema Camera footage is recorded as Blackmagic RAW or ProRes, which runs to tens of gigabytes an hour, so export the sound as a WAV or MP3 and upload that. A 2.5-hour sit-down interview then comes back as text in about 5 minutes, the first 20 minutes are free, and a $6 pack of 500 minutes covers the remaining 130.
From cinema clip to searchable text
The words live in the soundtrack, so send the soundtrack and leave the picture in the edit.
Why the clip will not go up as it is
A .braw file is camera raw that only editing software decodes, and a ProRes .mov from the same camera is still enormous. Arithmetic shows the problem: any video written at 400 Mbps fills 180 GB an hour (400 divided by 8, times 3,600 seconds). The upload limit is 5 GB per file, so the soundtrack is the part to send.
Exporting the soundtrack
Open the clips in your editor, put the interview on a timeline, and render audio only. In DaVinci Resolve that is the Deliver page with video unticked; menus move between versions, so check the export settings in yours. A 16-bit, 48 kHz stereo WAV is about 691 MB per hour, and an MP3 at 192 kbps about 86 MB.
A run of interviews
A documentary built on fourteen interviews of about 2 hours each is 1,680 minutes of speech. That sits inside the $12 pack of 2,000 minutes with 320 to spare for pickups. A single long interview needs only the $6 pack.
Selects without scrubbing
Each interview returns with a brief of the subject's main points, chapters with timestamps, key quotes, and the names, places and dates mentioned. Interviewer and subject are named in the summary, quotes and chapters, so the paper edit starts from text rather than from the timeline.
Cinema footage elsewhere
Raw camera files are built for grading, and transcription tools choke on them.
✗ Where cinema files trip up
Good sound, trapped inside a file nobody can upload.
- BRAW files that no transcription upload can read
- ProRes clips measured in tens of gigabytes
- The OpenAI Whisper API capped at 25 MB per upload
- Interviews chopped into short pieces to fit
- Timestamps that restart with every piece
- Hours of rushes logged by ear
✓ Audio out, text back
One export per interview, one transcript per export.
- WAV or MP3 rendered from the timeline
- Roughly 5 minutes for the 2.5-hour take
- Each file up to 10 hours
- One clock for the whole conversation
- The interview's first 20 minutes without charge
- $12 for a fourteen-interview film
Sample
A sit-down interview shot on a cinema camera, as it comes back.
This sample is illustrative, written for this page rather than taken from a real production. The timestamps reflect a 2.5-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
Blackmagic Pocket footage, the common questions.
How long until a 2.5-hour interview is text?
Expect about 5 minutes, since each audio hour takes close to 2. The public proof page shows a 4.94-hour file finished in 372 seconds.
What does a whole film's worth of interviews cost?
On a first visit, the opening 20 minutes of the interview cost nothing. One 150-minute interview fits the $6 pack of 500 minutes. Fourteen interviews of 2 hours, 1,680 minutes in all, belong on the $12 pack of 2,000 minutes, at $0.36 an audio hour.
Can I upload the ProRes .mov directly?
Only if it is under the size limit: up to 2 GB before your first pack and up to 5 GB once one is on the account, with 10 hours as the ceiling either way. Long ProRes clips pass that quickly, which is why an audio export is the dependable route.
The camera recorded the interview as several clips. What now?
Lay the clips end to end on a timeline and export the audio as one file, so the transcript runs on a single clock. Uploading each clip separately also works if you prefer one transcript per card.
What if the subject speaks another language?
99 languages are detected automatically, Japanese, Spanish and Korean among them. An interview that moves between two languages is detected on the one spoken most, and English mixed with Tagalog is handled.
Which files come back, and who hears the audio?
Five formats: TXT, DOCX, SRT, VTT and JSON, the SRT handy for a rough subtitle pass. Recordings are transcribed on our own servers and are never used for training, and an unreleased interview can be deleted along with its text.
Related
Related pages for long footage
Render the audio, then drop it here. Watch the first 20 minutes come back free.
Transcribe my Pocket interviewOperated by Neugence Technology Pvt. Ltd. · contact@whipscribe.com · Security · Privacy · Terms