Transcribe long Cloudflare Stream videos stored uploads and recorded live inputs.
A long video stored in Cloudflare Stream is transcribed from an MP4 download of it, and a 3-hour recorded live input comes back as text in about 6 minutes. The opening minutes are a free preview, and forty recorded product streams of 75 minutes (3,000 minutes) fit the $18 pack of 3,000 minutes, which includes API access.
From your Stream account to text
Stream stores and delivers the video. The words inside it are a separate job.
Getting an MP4 out
Stream serves video as adaptive streams, and a downloadable MP4 has to be created for each video, from the dashboard or through Cloudflare's API depending on the current options. Once it is ready, download it and upload it here. Check Cloudflare's documentation for the exact steps, since they change.
Recorded live inputs
When a live input is set to record, each broadcast is saved as a video in the account, and a long event can run for hours. Treat that recording like any other video: create its download and send it. The box here takes files up to 500 MB, and bigger downloads continue on the main upload page, up to 10 hours or 5 GB per file.
For teams that script things
The $32 pack of 6,000 minutes includes access to the WhipScribe API, so a developer can send files from your own code and read back the JSON, which carries the text with timestamps. There is no Cloudflare integration on our side: your script moves the file, and WhipScribe never reads your Stream account.
The arithmetic
One 3-hour live event is 180 minutes on the $4 pack of 300. A month of daily 1-hour standups recorded to Stream, about 22 of them, is 1,320 minutes on the $18 pack of 3,000.
Video as storage
Everything is stored and streamable, and none of it can be searched by what was said.
✗ Bytes, not words
The video plays perfectly; the content is opaque.
- No text to index for search
- Captions handled as a separate project
- Recorded events nobody rewatches
- Speakers' points lost after the stream
- Long recordings with no chapters
- Manual notes for every product stream
✓ Text alongside the video
Each MP4 returns transcript, captions, brief and JSON.
- About 6 minutes per 3-hour recording
- JSON with timestamps for your app
- SRT and VTT from the same run
- Speakers named in the summary and chapters
- Packs from $4 for 300 minutes
- Chapters for each recorded event
Sample
A recorded product livestream, as returned.
This sample is illustrative and was written for this page; it is not from any real Cloudflare customer or broadcast. Timestamps sit inside a 3-hour stream.
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 $4 (300 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
$4/300 min
5 hours of audio — $0.80 an hour. One-time — credits never expire.
- 300 minutes of audio
- All export formats
- AI chat over the whole transcript
- Executive summary & key quote
Best value
$18/3,000 min
50 hours of audio — $0.36 an hour. Credits never expire.
- 3,000 minutes of audio
- Summary, chapters and key quotes
- All export formats
- AI chat over the whole transcript
Bulk pack
$32/6,000 min
100 hours of audio — $0.32 an hour. Credits never expire.
- 6,000 minutes of audio
- Summary, chapters and key quotes
- API access for batch pipelines
- All export formats
FAQ
Cloudflare Stream recordings: common questions.
How long does a 3-hour Stream recording take?
About 6 minutes, because processing runs near 2 minutes per hour of audio. A full-day 8-hour event recording takes around 16.
Can I paste a Stream playback URL?
Stream playback addresses are not one of the supported link sources, so create the MP4 download and upload it. If the same event was simulcast to YouTube or Twitch, paste that link instead.
Does WhipScribe integrate with Cloudflare?
No. There is no integration, worker or plugin. Your team downloads the file, or a script you write sends it through the WhipScribe API, which comes with the $32 pack.
How large is a long MP4 download?
It depends on the rendition you download. Three hours at 1080p and 4 Mbps is about 5.4 GB, over the 5 GB per-file ceiling, so take a 720p rendition (about 3.4 GB at 2.5 Mbps) or an audio-only file. Files up to 5 GB upload with or without a pack.
What does a whole archive cost?
The opening minutes are a free preview. One 3-hour event uses the $4 pack of 300; twenty-two 1-hour standups use the $18 pack of 3,000; forty 75-minute streams use the $32 pack of 6,000. Packs are one-time and credits never expire.
Which exports, and where is the audio processed?
TXT, DOCX, SRT, VTT and JSON. Recordings are transcribed on our own servers and are never used for training, and you can delete any file and its transcript.
Related
More video platforms
Download the MP4 from Stream and drop it here. Your recording starts with a free preview of its opening minutes.
Transcribe my Stream videoOperated by Neugence Technology Pvt. Ltd. · contact@whipscribe.com · Security · Privacy · Terms