Transcribe long recordings from Kdenlive render the audio, keep the edit.
To transcribe a long Kdenlive project, render it as audio only and upload that file, up to 10 hours or 5 GB; a 2.5-hour cut comes back as text in about 5 minutes. At 192 kbps the render is about 216 MB, and its 150 minutes fit the $6 pack of 500 minutes once the first 20 free minutes are used.
From the timeline to text
The transcript only needs the sound, so render the sound and nothing else.
Rendering audio only
Open the render dialog from the Project menu and look for an audio-only preset such as MP3; the exact list depends on your Kdenlive version, so check the render settings if you do not see one. A full video render works too, it is simply larger and slower to upload. WhipScribe has no add-on inside Kdenlive and reads only the file you render.
Why the audio render is so small
At 192 kbps, a second of MP3 is 24,000 bytes and an hour is 86.4 MB, so a 2.5-hour edit renders to about 216 MB. The same edit as a high-bitrate video can run to several gigabytes, which is why rendering audio only is the faster route on a home connection.
Subtitles that match the cut
Because you upload the finished edit, the SRT and VTT files line up with your timeline rather than with the raw footage. Import them back into Kdenlive as a subtitle track, or hand them to whoever publishes the video.
A documentary series on one pack
Eight episodes of 2.5 hours each add up to 1,200 minutes, beyond the $6 pack. The $12 pack of 2,000 minutes covers all eight at $0.36 an audio hour and leaves 800 minutes for the next cut. One episode on its own fits the $6 pack.
Long edits elsewhere
Long Linux edits tend to stall at the export, not in the timeline.
✗ The usual detour
Hours of edit, no words to search.
- Rendering a huge video just to transcribe it
- Upload pages that cap at an hour
- The Whisper API's 25 MB ceiling
- Splitting the timeline into parts
- Subtitles timed to raw footage, not the cut
- Logging every answer by hand
✓ With an audio render
A small file, the whole edit in text.
- About 216 MB for 2.5 hours
- Text in roughly 5 minutes
- SRT and VTT timed to the final cut
- Interviewees named in summary and chapters
- 150 minutes taken from $6
- JSON for your own scripts
Sample
An edited long-form interview, as it comes back.
Illustrative lines written for this page; no real film or interviewee is quoted. Timestamps show a 2.5-hour 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
Kdenlive renders, the common questions.
How long does a 2.5-hour Kdenlive render take to transcribe?
About 5 minutes at roughly 2 minutes per audio hour. The proof page records a 2.48-hour file finished in 200 seconds.
What does a long edit cost, and which pack fits?
If you are new here, the first 20 minutes of the render are free. A 2.5-hour edit is 150 minutes, which belongs on the $6 pack of 500 minutes, and eight such episodes, 1,200 minutes, belong on the $12 pack of 2,000 minutes.
How large can the render be?
A render can be up to 5 GB or 10 hours. Until a pack is on the account a render may be up to 2 GB; a bigger one starts once a pack is bought. An audio-only render keeps you far below every limit.
My project runs longer than 10 hours. What do I do?
Render it in two parts at a natural break, using a zone or a range on the timeline, and upload each part. Each comes back with its own brief and chapters.
Does it handle interviews in other languages?
Yes, 99 languages are detected automatically. An interview that moves between two languages is detected on the main one, and the switches are handled.
Which files come back, and is the footage private?
The render comes back as TXT, DOCX, SRT, VTT and JSON. Recordings are transcribed on our own servers and are never used for training, so an unreleased film stays unreleased.
Related
Other editors and long files
Render the audio and send it. Your first 20 minutes of footage are free.
Transcribe my Kdenlive renderOperated by Neugence Technology Pvt. Ltd. · contact@whipscribe.com · Security · Privacy · Terms