Transcribe recordings made in a café over the sound of the espresso machine.
An interview recorded in a café comes back as text at about 2 minutes per hour of audio, so a 75-minute conversation is ready in roughly 2.5 minutes. The opening 20 minutes cost nothing, and a $6 pack of 500 minutes finishes that interview with most of the pack left.
What a café does to the audio
The grinder, the steam wand, the table next to you.
Noise that is not your interview
A café layers a grinder, a steam wand, cups on saucers, background music and other people's conversations. Music never reaches the text. The voices that come through are the ones nearest the phone, so put it between you and the interviewee, not by the window or the counter.
Quotes you can stand behind
Each key quote carries a timestamp, so a line you want to print can be checked against the recording in seconds. Speakers are named in the summary, key quotes and chapters, which keeps interviewer and source apart.
A study's worth of interviews
Twenty-five research interviews of an hour each come to 1,500 minutes. That sits on the $12 pack of 2,000 minutes, at $0.36 an audio hour, with room left for follow-ups.
The interview, mapped
Chapters mark where the conversation turned, and the brief lists the names, figures and dates the source gave. The chat answers questions such as what they said about the timeline, quoting the passage it found.
Why café interviews go wrong elsewhere
Background chatter and a long conversation, both at once.
✗ Where it breaks
Short-clip tools struggle with the length, and typing it yourself means replaying every noisy patch.
- Free plans capped at 30 minutes
- Replaying a passage three times by hand
- A neighbouring table typed into the text
- No timestamp to check a quote
- A monthly plan for a handful of interviews
- Raw text and nothing else
✓ The interview, readable
One upload per interview, and the conversation comes back in order.
- About 2.5 minutes for a 75-minute interview
- The first 20 minutes free
- A $6 pack of 500 minutes
- Music in the background left out
- Timestamped quotes
- Exports for your notes or editor
Sample
A research interview in a café, as it comes back.
This sample is illustrative and written for this page; it is not a customer recording. It shows how a long interview over coffee reads.
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
Café recordings, the common questions
How long does a café interview take to transcribe?
It runs at close to 2 minutes for every hour of sound. A 75-minute interview is ready in roughly 2.5 minutes, and a two-hour one in about 4. If you step away, the finished interview sits in your Library.
What does a set of interviews cost?
A single 75-minute interview fits the $6 pack of 500 minutes after the first 20 minutes free. Twenty-five hour-long interviews, 1,500 minutes, belong on the $12 pack of 2,000. Above 2,000 minutes, the $24 pack holds 5,000 and includes API access.
Is there a size limit for the recording?
The per-file limit is 10 hours of audio or 5 GB, whichever arrives first. Without a pack yet, the upload limit is 2 GB; anything above that starts once a pack has been added. A phone or recorder interview is well within that.
Should I cut out the noisy parts first?
No. Upload the whole interview as one file. Background noise is not transcribed, and cutting the audio would break the timestamps you need to check quotes. Only a recording past 10 hours needs to go in as two files.
Can it handle an interview in another language?
Yes. 99 languages are detected automatically, so you do not choose one first. An interview is detected on its main language, and English with Tagalog switching in the same conversation is handled.
What can I export, and who else hears the interview?
TXT, DOCX, SRT, VTT and JSON from a single run. Interviews are transcribed on our own servers and are never used for training, and you can delete the file and transcript at any time.
Related
Other places interviews happen
Upload the interview. Start with the first 20 minutes free.
Transcribe a café recordingOperated by Neugence Technology Pvt. Ltd. · contact@whipscribe.com · Security · Privacy · Terms