Transcribe a long Riverside episode and pick the right download.
A long Riverside episode transcribes from one upload of the mixed recording, and a 2-hour episode is ready in about 4 minutes. The first 20 minutes are free and the $6 pack of 500 minutes covers the rest; uploading each guest's separate track instead also works, but every track is counted at its full length.
Riverside gives you choices
Separate tracks are great for editing. For a transcript, the choice of file changes both the reading and the bill.
Mixed file for the conversation
The mixed recording has every voice on one timeline, so the transcript reads in the order the conversation happened and the brief can name each guest in it. It also counts once: a 2-hour episode is 120 minutes whatever the number of people on the call.
Tracks when you need one voice
Each participant's track is a file of its own, and each becomes a separate transcript with its own clock. That suits pulling one guest's answers for a profile or a quote card. Three tracks from a 2-hour session count as 360 minutes, because each one runs the full length.
Large WAV downloads
Riverside's per-participant audio is often a high-quality WAV, which runs to several hundred megabytes an hour. A long episode can therefore be a big file even with no video in it. A download larger than the box takes continues on the upload page, up to 5 GB per file.
From recording to show notes
The episode comes back with a brief that states the thesis and takeaways, chapters with timestamps for the description, the names, numbers and dates each guest mentioned, and the questions the conversation answered. Quotes carry the speaker's name, so they go straight into a post.
Where long remote episodes slow down
The recording took two hours. The write-up should not take two days.
✗ Tracks without text
The edit is done, but the notes, quotes and description still have to be written by ear.
- Listening back to find the best quote
- Separate tracks that need mixing first
- Show notes typed up from listening back
- Large WAVs most tools refuse
- No chapters for the episode page
- A per-hour bill for every guest's track
✓ One mix, one transcript
The mixed file goes up once, and the episode comes back ready to write from.
- A two-hour episode in about 4 minutes
- Counted once, not once per guest
- 20 opening minutes free
- Guests credited by name in the brief
- Chapters for the description
- SRT and VTT for the video cut
Sample
A long remote interview, forty minutes in.
This sample is illustrative and was written for this page, not taken from a real Riverside episode. The timestamps run from the start of the mixed recording.
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
Riverside recordings, the common questions.
How long does a 2-hour Riverside episode take to transcribe?
About 4 minutes after upload, at roughly 2 minutes per hour of audio. A 3-hour conversation takes about 6, and a 5-hour recording day about 10. You can leave the page while it runs.
How are separate tracks counted?
Every file is counted at its own length. A 2-hour episode with three participants is 120 minutes as one mixed file, or 360 minutes as three tracks. Both fit the $6 pack (500 minutes), but over a season the mixed file stretches the minutes three times as far.
What does a full season of two-hour episodes cost?
Twenty 2-hour episodes are 2,400 minutes as mixed files, which is more than the $12 pack (2,000 minutes), so that season goes on the $24 pack (5,000 minutes). Credits never expire, so whatever is left carries over to the next season.
How big can a Riverside download be?
Each download can be up to 10 hours or 5 GB, whichever comes first. Until a pack is on the account, uploads stop at 2 GB; anything larger begins after the first pack. If a video download is too big, the audio-only file gives the same transcript.
What if a guest speaks another language?
The language is detected automatically from 99, so an episode in Spanish, Hebrew or Swedish needs no setting. When a guest switches language partway, the recording is detected on its main language; English and Tagalog together are handled.
Which exports are included, and who can see the episode?
One run yields TXT, DOCX, SRT, VTT and JSON for the episode. Riverside downloads are transcribed on our own servers and are never used for training, and you can delete an episode and its transcript at any time.
Related
More for remote recordings
Upload the mix. Read 20 minutes before paying anything.
Transcribe my Riverside episodeOperated by Neugence Technology Pvt. Ltd. · contact@whipscribe.com · Security · Privacy · Terms