Transcribe Obsidian audio recordings and put the words back in the note.
A long recording made with Obsidian's audio recorder is saved as a file in your vault, so you can upload that file here, up to 10 hours or 5 GB, and a 2-hour meeting comes back as text in about 4 minutes. Four weekly 2-hour sessions total 480 minutes, which fit the $6 pack of 500 minutes after the first 20 minutes free.
From the vault to the note
Obsidian already keeps the recording as a plain file; that makes the round trip short.
Finding the file
The recorder embeds the audio in the note and stores the file in your vault, usually in the folder set for new attachments under Files and links. On a desktop, right-clicking the file in Obsidian's file pane usually offers to reveal it in the system file browser. On a phone, the vault folder is reachable from the Files app or a file manager, depending on where the vault lives.
Format, and when to convert
On many desktops the recording is a WEBM file, while some phones save M4A; check the extension in the vault before you upload. Both go up as they are. If a file ever refuses, convert it to MP3 in an audio tool and try again. Upload it on upload page or drag it into the box above.
Back into Markdown
Download the transcript as TXT and paste it under the embed, or keep the brief and chapters at the top of the note and link the full text below. Timestamps in the chapters let you jump to the right minute in the embedded audio. WhipScribe has no Obsidian plugin; this is a manual copy, and it stays your file.
A reading group, priced
A group that meets for 2 hours a week records 480 minutes a month, inside the $6 pack of 500 minutes at $0.72 an audio hour. A full term of fourteen sessions, 1,680 minutes, fits the $12 pack of 2,000 minutes.
Audio in a knowledge base
A 2-hour recording embedded in a note is the one part of the vault search cannot read.
✗ Audio in the vault
Linked from a note, never searched.
- Vault search that skips everything in the audio
- Replaying two hours for one remark
- Uploads blocked by the Whisper API at 25 MB
- Clipping the audio into short parts by hand
- Notes typed during the meeting with gaps
- Links to recordings nobody opens
✓ Text beside the audio
The recording, searchable like the rest.
- The vault file uploaded unchanged
- The session readable 4 minutes after upload
- Chapters to paste as headings
- Names and dates said, as a list
- Weekly sessions on the $6 pack
- TXT that pastes cleanly into Markdown
Sample
A recorded reading-group session, returned as text.
These lines are illustrative and were written for this page; they quote no real group or person. Timestamps come from a 2-hour session.
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
Obsidian audio recordings, answered.
Is there a WhipScribe plugin for Obsidian?
No. WhipScribe has no plugin or integration for Obsidian. You upload the audio file from the vault and paste or save the transcript back yourself, which keeps the vault entirely under your control.
How long does a 2-hour recording take?
Close to 4 minutes, because an hour of audio takes about 2. A 30-minute voice note is back in about a minute, and a 5-hour workshop in about 10.
What will a term of sessions cost?
New visitors get the first 20 minutes free, and a longer file is previewed until a pack from $6 transcribes the remainder. A month of weekly 2-hour sessions is 480 minutes on the $6 pack of 500 minutes, and fourteen of them sit on the $12 pack of 2,000 minutes. Credits never expire.
My vault syncs through Google Drive. Can I paste a link?
Yes, a Google Drive share link to the audio file works, and nothing needs to be downloaded first. Make sure the link's sharing setting lets anyone with the link open it.
What if a vault recording runs past 10 hours?
One file may run 10 hours or 5 GB, whichever comes first, and up to 2 GB before your first pack. Split anything longer into two files and transcribe each; the language is detected automatically from 99.
Which exports are offered, and is my audio private?
Downloads come as TXT, DOCX, SRT, VTT or JSON, ready to paste. The audio is transcribed on our own servers and never used for training, which suits a vault kept local by choice, and you can delete the recording and its text at any time.
Related
More notes apps with long audio
Make the recording searchable in your vault. Your vault's first 20 minutes are free.
Transcribe my Obsidian recordingOperated by Neugence Technology Pvt. Ltd. · contact@whipscribe.com · Security · Privacy · Terms