Transcribe long Adobe Audition sessions one mixdown, every voice.
For a long Adobe Audition multitrack session, export a mixdown of the entire session as WAV or MP3 and upload it; a 3-hour session returns as text in about 6 minutes. The first 20 minutes are free, and the $6 pack of 500 minutes covers that session with 320 minutes left.
Session to transcript
Send the mix you would publish, not the session folder.
Export the mixdown
An Audition session file points at separate track files, so it cannot be transcribed on its own. In the Multitrack view, the export menu offers a multitrack mixdown of the entire session; save it as WAV or MP3 and upload that single file. Check the export settings for the format before you click OK.
Watch the size of a WAV
At 24-bit, 48 kHz stereo, a WAV runs about 1.04 GB an hour, so a 3-hour mixdown is near 3.1 GB. That is under the 5 GB cap but over the 2 GB that uploads before a pack. A 128 kbps MP3 of the same session is about 173 MB.
Pricing a run of sessions
One 3-hour session is 180 minutes on the $6 pack. Ten four-hour sessions add up to 2,400 minutes, past the $12 pack's 2,000, so that series fits the $24 pack of 5,000 minutes with 2,600 minutes left over.
A paper edit before the cut
Chapters with timestamps let you find the strong passage in hour two without scrubbing. The brief, the quotes and the list of names, numbers and dates give you an edit plan, and the chat finds the moment a guest said something you remember.
Long sessions in other tools
A multitrack session is long, heavy and split across files.
✗ The usual workaround
Small upload caps meet a large WAV.
- Uploading each track separately
- Hitting a 25 MB cap on the Whisper API
- Bouncing the session in 30-minute parts
- Lining timestamps up by hand
- Scrubbing the waveform for one quote
- An edit plan written from memory
✓ With one mixdown
A single file holds the whole conversation.
- WAV or MP3 mixdown, uploaded whole
- The mix as text about 6 minutes on
- One timeline from start to end
- Chapters to plan the cut
- Each quote tied to its time in the mix
- $6 covers a 3-hour session
Sample
A long interview session, mixed down from Audition.
The lines below are illustrative and were made up for this page. It does not come from a real production. Timestamps show a 3-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
Adobe Audition sessions, answered.
How long does a 3-hour Audition mixdown take?
Around 6 minutes. Transcription runs at about 2 minutes per audio hour, and a 9.31-hour file finished in 1,033 seconds on the proof page.
What does a series of long sessions cost?
The first 20 minutes are free, which is enough to judge a mixdown before you pay. A 3-hour session uses 180 of the $6 pack's 500 minutes. A series up to 2,000 minutes fits the $12 pack, and the $24 pack holds 5,000 minutes at $0.29 an audio hour.
My WAV mixdown is 3 GB. Will it be accepted?
Yes, once a pack is on the account, because files over 2 GB start after the first pack. Every file can be up to 5 GB. Exporting the mixdown as MP3 brings it far under 2 GB.
Do I upload each track or the mix?
The mix. Upload one mixdown of the entire session; separate tracks would each be transcribed on their own, without the conversation between them. A session over 10 hours goes up as two mixdowns.
Which languages work?
99 languages, recognised automatically from the audio itself. An interview in Hebrew, Japanese or Portuguese needs no setting.
Exports and privacy?
TXT, DOCX, SRT, VTT and JSON come back from each mixdown, and the DOCX opens in any word processor for a paper edit. Sessions are transcribed on our own servers and are never used for training.
Related
More editing software and long audio
Export one mixdown of the session. Its first 20 minutes are free to try.
Transcribe my Audition mixdownOperated by Neugence Technology Pvt. Ltd. · contact@whipscribe.com · Security · Privacy · Terms