Box · shared file links

Transcribe a recording from a Box shared link.

WhipScribe transcribes an audio or video file from a Box shared link set to People with the link. Packs: $4 for 300 minutes, $18 for 3,000, $32 for 6,000; Workspace $19 a month. Up to 10 hours or 5 GB per file. Measured turnaround: about 2 minutes per audio hour. 99 languages. Checked 2 Nov 2026.

Free preview of the opening minutes Up to 10 hours or 5 GB per file 99+ languages TXT · DOCX · SRT · VTT · JSON

The file you have

Which Box links work.

Works: A shared link to one file (app.box.com/s/…) whose access is People with the link. Inside a shared folder, open the recording first so the address ends in /file/<number>, and paste that.
Does not work: A link to a whole folder (the fetch fails with 'not a file'), and links set to People in your company or Invited people only, which open only after a Box sign-in.
Typical files: Interviews, trainings and town halls kept as MP4, M4A, MP3 or WAV; all of them upload or fetch as they are.
When the option is missing: Box lets administrators remove 'People with the link'. Then download the file and upload it.

Sometimes a link works. Paste the file's shared link in the box above; a folder or sign-in-only link has to be replaced by the file's own open link, or by the file.

How it works

Three steps, the first one is the only one that takes any thought.

Set the shared link

Select the file → Share → Shared link → People with the link (Can view or download).

Copy and paste it here

The file is fetched from Box. About two minutes of processing per hour of audio once it arrives.

Close the link afterwards

Set the link back to Invited people only once the transcript is made.

Good to know

What trips people up, and what to do about it.

Some organisations default new links to Invited people only (UW–Madison did from April 2024, for example). That link needs a Box sign-in, so it fails here; change it to People with the link for the fetch.
Password-protected links and links with download switched off cannot be read by a tool. Remove the password or allow download for the fetch, or download the file yourself.
Many recordings in one folder? Each file needs its own link. For a whole archive, download the folder and upload the files; each becomes its own transcript in your library.

Example. A research team keeps 40-minute participant interviews in a Box folder. A researcher opens one recording, sets its link to People with the link, pastes the file address here, and gets the transcript with timestamps for coding the quotes.

What comes back

More than a wall of text.

The same four things for every Box recording, whatever its length.

A transcript with timestamps

Every line carries its time. Click a line to hear that second again, or search a name or phrase and jump to each place it was said.

A summary, chapters and key quotes

A brief with the takeaways, chapters with their start times, and the quotes worth keeping. Speakers are identified and named in the summary, key quotes and chapters.

Questions answered from the recording

Ask where a topic came up or what was decided, and get the answer with the time it was said, instead of scrolling the whole text.

Every export

TXT, DOCX, SRT, VTT, JSON from the same transcript: a document to edit, caption files for video, plain text to paste, structured data for your own tools.

Pricing

Free preview. Packs from $4, and the minutes never expire.

A 40-minute interview is 40 minutes, so the $4 pack (300 minutes) covers it 7 times over. Every recording gets a free preview, and in 31 countries, or for recordings of an hour or more in most others, a summary you can read before paying; a pack opens the full transcript and every export. Packs are one-time purchases with no subscription and no seat fee.

$4300 minutesBuy $183,000 minutesBuy $326,000 minutesBuy

Pick a pack to open secure checkout. Workspace is $19 a month for unlimited transcription (300-hour fair-use mark). Full pricing

What we measured, last 30 days

3,332 recordings, 2,490 audio hours, 65 languages detected. An hour of audio came back in 3.1 minutes for half of the recordings and within 17.5 minutes for nine in ten, measured from the moment the file landed to the finished transcript. Refreshed 2026-10-28; method on how we test.

FAQ

Box to text, answered.

Can I paste a Box link instead of downloading?

Yes, for a link to one file set to People with the link and allowing download. Folder links and links that need a Box sign-in cannot be read by any tool.

Why does my Box link fail as not a file?

It points at a folder. Open the recording inside the folder and copy that address, which ends in /file/ and a number, or share the file on its own.

What does transcribing Box recordings cost?

The preview is free, and so is the summary in 31 countries or for recordings of an hour or more. A pack opens the full transcript: $4 for 300 minutes, $18 for 3,000 minutes, $32 for 6,000 minutes. Packs are one-time, credits never expire, and Workspace is $19 a month if you transcribe every week.

How long can the recording be?

One file can run up to 10 hours or 5 GB. The box on this page takes files up to 500 MB; a larger file continues on the main upload page, which uploads it in parts. Most recordings come back in about two minutes per hour of audio.

Is the recording kept private?

Recordings are transcribed on our own servers and are never used for training. You can delete a recording and its transcript at any time.