How to transcribe a recording with many speakers keep it in one file.
Upload the whole session as one file: the speakers are identified and named in the summary, key quotes and chapters, and the transcript runs with timestamps, for files up to 10 hours or 5 GB (2 GB before your first pack) at about 2 minutes per audio hour. A 3-hour panel with eight voices is 180 minutes on the $6 pack of 500, and the first 20 minutes are free.
Many voices, one recording
What to do before, during and after a session with a full table.
Before: ask for introductions
When each person says their name and role at the start, the summary and key quotes have names to attach to what they said. It takes a minute of the recording and saves a lot of guessing later. For a public panel, the chair reading out the names does the same job.
During: one voice at a time
Crosstalk is the hardest thing in any multi-voice recording. A chair who repeats questions from the floor, a microphone in the middle of the table rather than at one end, and a pause before replies all help more than any setting afterwards.
After: read the summary first
The brief gives the thesis and takeaways; the chapters split the session by topic with timestamps; the key quotes carry the speaker's name. The transcript itself is continuous timestamped text, so to attribute a line, find it in the quotes or chapters, or listen at its timestamp.
Large files, one upload
A full-day workshop or a council session can be several hours of video. One file takes up to 10 hours or 5 GB; before your first pack the limit is 2 GB. The box here accepts up to 500 MB, and a larger file continues on the main upload page.
Group recordings
Splitting a group session by person usually loses the thread.
✗ Habits that cost clarity
What makes multi-voice files harder.
- One phone at the chair's end of the table
- No introductions at the start
- Everyone answering at once
- Cutting the session into many clips
- Questions from the floor left unrepeated
- Attributing quotes from memory
✓ What works
Simple choices that carry through to the text.
- A microphone in the middle of the room
- Names said once at the start
- The whole session as one file
- Speakers named in the summary and quotes
- Chapters by topic with timestamps
- Doubtful attributions checked by ear
Sample
A five-person discussion, as text.
An illustrative excerpt written for this page; the discussion is invented.
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
- AI chat over the whole 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
- Summary, chapters and key quotes
- All export formats
- AI chat over the whole transcript
Bulk pack
$24/5,000 min
83 hours of audio — $0.29 an hour. Credits never expire.
- 5,000 minutes of audio
- Summary, chapters and key quotes
- API access for batch pipelines
- All export formats
FAQ
Many speakers: the follow-up questions.
How do I transcribe a recording with many speakers?
Upload the whole recording as one file. Speakers are identified and named in the summary, key quotes and chapters, and every passage keeps its timestamp. Files can run to 10 hours or 5 GB.
Does each line of the transcript show a name?
No. The names appear in the summary, key quotes and chapters. The transcript is continuous text with timestamps, which you can use to go back to the audio and confirm who was talking at that moment.
Does a larger group cost more?
No. Price depends only on running time. Six 90-minute focus groups are 540 minutes, just over the smallest pack, so they go on the $12 pack of 2,000. Twenty-four 3-hour council meetings are 4,320 minutes on the $24 pack of 5,000.
Should I record each person on a separate microphone?
If you already have separate tracks, a mixed-down file with everyone in it is usually the best upload, because the conversation stays in order. A single clean room recording also works well when people speak one at a time, and it is far simpler to manage across a series of sessions.
What about a hybrid meeting with remote participants?
Record the call itself if you can, with the consent of everyone present that the law where you are requires. That recording usually captures remote and room voices more evenly than a phone left on the table.
Which exports come with it, and who sees the recording?
TXT, DOCX, SRT, VTT and JSON. Recordings are transcribed on our own servers and never used for training.
Related
Related pages on group recordings.
A full table of voices? One file, first 20 minutes free.
Transcribe the sessionOperated by Neugence Technology Pvt. Ltd. · contact@whipscribe.com · Security · Privacy · Terms