Drop a meeting recording get notes that finish themselves.
Summary, action items, decisions, and a speaker-labelled transcript — generated from your Zoom, Google Meet, or Teams recording. We don't join your call; you record it and drop the file.
What you get
What real meeting notes need to be useful.
Decisions and follow-ups, extracted
Beyond a summary — we pull out every explicit decision ('we'll go with vendor B'), every action item ('Priya owns the Q3 spec by Friday'), and every open question. Each one is linked back to the timestamp where it was said.
Up to 8 speakers, labelled
Diarization handles the standard meeting case — 3 to 5 people on a Zoom — and stretches to 8. Each speaker gets a stable label across the whole transcript, so 'Speaker 3' is the same person at minute 2 and minute 47.
You record, we transcribe
We don't send a bot to join your call — that's a privacy tradeoff we won't make. You record locally in Zoom / Meet / Teams (one click in each), drop the file here, and the notes come back. Your call audio never leaves your control until you choose to upload it.
DOCX-ready for the share-out
Export DOCX with a clean header, summary section, action items as a checklist, and the full transcript as an appendix. Drops straight into a Notion / Google Doc / Confluence page — no reformatting, no copy-paste cleanup.
Why summary alone isn't enough
A summary vs notes someone can act on.
✗ Generic AI meeting summary
Five bullet points about what was discussed. Often paraphrased imprecisely, with action items missed and the actual decisions lost in the prose.
- No clear action items with owners
- Decisions buried in narrative prose
- No timestamps to verify
- Names and titles often hallucinated
- Skips the follow-up questions
✓ Whipscribe meeting notes
Summary, decisions, action items with owners, and open questions — each anchored to a timestamp in the full speaker-labelled transcript. You can verify every claim against the audio.
- Action items with owner + due date
- Decisions called out separately
- Every claim links to a timestamp
- Open questions tracked
- Full transcript as appendix
Sample output
Speaker-labelled. Action items pulled out.
This is what the start of a typical meeting transcript looks like — the action item extractor reads the same text the human reader does.
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
Word-level. Every video editor reads this.
WebVTT
HTML5 player + YouTube uploads.
Show notes
Formatted with chapters and pull-quotes.
Machine-readable
Per-word timing + speaker IDs.
Pricing
Honest pricing, no surprises.
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. One-time — credits never expire.
- 300 minutes of audio
- All export formats
- Unlimited Claude 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 Claude 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
Meeting notes questions, answered.
Do you train AI on my meeting audio?
No. We never use customer audio or transcripts to train any model — yours or anyone else's. This is a hard policy, not a setting. The audio is used only to generate your transcript and notes; files in your library are retained for 365 days and you can delete any item from settings.
Are you HIPAA or SOC2 compliant?
Honest answer: not yet. We are not HIPAA-certified and our SOC2 Type II is in progress (target Q4 2026). For HIPAA-regulated workloads (PHI, clinical recordings) we recommend a HIPAA-certified vendor. For most internal meetings — product, sales, hiring — our standard infrastructure is appropriate.
Do you join my call as a bot?
No. We don't send a bot to your Zoom / Meet / Teams call. You record locally (Zoom: 'Record', Meet: 'Recording on', Teams: 'Start recording'), the file lands in your folder, and you upload it here. This is a deliberate choice — bots that join calls have to be granted permissions we'd rather not hold.
How many speakers can it label?
Up to 8 distinct speakers per recording with stable labels across the whole transcript. Beyond 8 (large town halls, all-hands), the labels start merging similar voices. For 1-on-1s and standard team meetings, expect very clean separation.
Will it work for a non-English meeting?
Yes — auto-detect picks the language from the audio. Whisper-large-v3 covers 100+ languages. The summary and action item extraction are LLM-driven and work best in English, Spanish, French, German, Portuguese, and Hindi. For other languages the transcript is solid; the summary may be less precise.
Where do my files go after upload?
Files in your private library are retained for 365 days; you can delete any item from your account settings. We never share files with third parties or use them for training.
Related
Related tools and pages.
Drop a meeting. Get notes you can ship.
Try WhipscribeOperated by Neugence Technology Pvt. Ltd. · contact@neugence.ai · Security · Privacy · Terms