Transcribe long interviews and events edited in DaVinci Resolve render audio, get text.
Render a long DaVinci Resolve timeline as audio only or as a small MP4 from the Deliver page, then upload it; a 7-hour event edit comes back as text in about 14 minutes. The first 20 minutes are free, and the $6 pack of 500 minutes covers it with 80 minutes left.
Edit to transcript
The picture is not needed for a transcript, so leave it out.
Render audio only
On the Deliver page, turn off the video export and keep the audio, then pick a format such as WAV or an AAC in an MP4 container in the render settings. Add the job to the render queue and render. The file lands in the location you set in the render settings.
Or a small MP4
If you want the picture alongside the text, render a 720p H.264 MP4 at a low bitrate. At about 4 Mbps a 7-hour edit is near 12.6 GB, too large, while audio only at 16-bit, 48 kHz stereo is about 4.8 GB. An AAC audio-only render at 192 kbps is about 600 MB.
The cost of a long edit
A 7-hour event uses 420 minutes, which fits the $6 pack with 80 left. A project of twelve 2-hour interviews is 1,440 minutes on the $12 pack of 2,000, with 560 minutes to spare.
A paper edit and captions
Chapters with timestamps and a brief of the takeaways give you a paper edit before you touch the timeline. Export SRT to import subtitles back into Resolve, and use the key quotes to pick soundbites by time.
Long edits elsewhere
A 7-hour timeline exported at full quality is far too big to send anywhere.
✗ The usual friction
Huge video files for a job that needs only the sound.
- Master-quality renders over 50 GB
- A Whisper API cap of 25 MB
- Footage cut into short exports
- Subtitles typed against timecode
- Soundbites found by scrubbing
- Interviews logged by an assistant
✓ With an audio-only render
Only the speech goes up, in one file.
- Audio-only or a small MP4
- A long edit read in about 14 minutes
- Up to 5 GB per render
- SRT back into the timeline
- Quotes with timestamps
- $12 for twelve 2-hour interviews
Sample
A long conference edit rendered from Resolve.
This sample is illustrative and written for this page, not taken from a real event. Timestamps show a 7-hour event edit.
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
DaVinci Resolve edits, answered.
How long does a 7-hour render take?
About 14 minutes, since transcription runs at roughly 2 minutes per audio hour, and an audio-only render uploads far faster than video. A 2-hour interview takes about 4 minutes.
What will the edit cost?
New visitors transcribe the first 20 minutes free. A 7-hour edit uses 420 minutes of the $6 pack. Twelve 2-hour interviews fit the $12 pack of 2,000 minutes, and a bigger project fits the $24 pack.
How large can the render be?
Up to 5 GB or 10 hours per render, whichever is reached first. Files up to 2 GB upload before a pack, and a larger file starts once one is on the account. Audio-only renders stay well inside both limits.
Do I need to split a long timeline?
Only past 10 hours, which few event edits reach. Use in and out points on the Deliver page to render two halves, and upload both.
Which languages can the footage be in?
99 of them, detected automatically, with no project setting to change. Interviews that switch language are transcribed on the main language spoken.
What do I get back, and is the footage private?
Each render returns TXT, DOCX, SRT, VTT and JSON, and the SRT imports into Resolve as a subtitle track. Footage is transcribed on our own servers and never used for training.
Related
More editing tools and long video
Render the audio and upload it. Your first 20 minutes are on the house.
Transcribe my Resolve renderOperated by Neugence Technology Pvt. Ltd. · contact@whipscribe.com · Security · Privacy · Terms