Transcribe long X Spaces recordings every speaker who took the mic.
A recorded X Space (formerly Twitter Spaces) transcribes from the host's downloaded copy, and a 3-hour Space comes back in about 6 minutes. The first 20 minutes are free, and the $6 pack of 500 minutes covers that Space with 320 minutes to spare.
From the Space to the text
A Space is talk from start to finish, which is exactly what transcription is for.
Getting the recording
Hosts who record a Space can usually get a copy of it from their own account; check X's current download options, since they change. The file is audio only. Should the upload refuse the Space file, convert it to MP3 first.
Many voices, one record
A Space can pass the mic to a dozen people in an evening. The summary, key quotes and chapters name who said what, so a long room with rotating speakers still reads in order.
Sized for audio
Audio-only files are small: an MP3 at 128 kbps is 128,000 bits a second, about 57.6 MB an hour, so a 4-hour Space is roughly 230 MB. That is far under the 2 GB that uploads before a pack.
What the Space becomes
Each Space returns a brief with its thesis and takeaways, chapters with timestamps, and the names, numbers and dates people said. Turn it into a thread, a newsletter recap or show notes, and ask the chat who argued which side.
Spaces elsewhere
A three-hour Space is gone from memory by the next morning, and most tools cannot take it in one piece.
✗ The usual outcome
Hours of conversation with no record anyone can search.
- The Whisper API from OpenAI refuses files over 25 MB
- A 4-hour Space at 128 kbps is about 230 MB
- Replaying the Space to find one claim
- Quotes attributed to the wrong person
- Notes from memory, the next day
- Recaps that skip the second half
✓ With the recording
The full Space, start to close, in one file.
- Up to 10 hours in one upload
- About 6 minutes for 3 hours
- Speakers named in the summary
- A chapter whenever the topic turns
- 20 minutes free on a first visit
- Text ready for a recap thread
Sample
An X Space, as it comes back.
This sample is illustrative, written for this page and not from a real Space. The timestamps follow a 3-hour room.
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
X Spaces recordings, the common questions.
How long does a 3-hour Space take?
About 6 minutes, because processing takes roughly 2 minutes per audio hour. The public proof page shows a 2.48-hour file finished in 200 seconds.
What does a series of Spaces cost?
The first 20 minutes are free the first time you visit. A 3-hour Space uses 180 minutes of the $6 pack of 500. A weekly 2-hour Space for three months is 13 × 120 = 1,560 minutes, which fits the $12 pack of 2,000.
Can I paste the link to the Space?
X links are not read directly, so download the recording and upload it. If you republished the Space as a podcast episode or a YouTube video, paste that link instead.
Is there a length limit?
Each file can run to 10 hours or 5 GB. A Space that ran past 10 hours goes in as two files. An audio-only Space rarely comes near the size limit.
Does it handle accents and other languages?
The language is detected automatically from 99. A room that drifts between two languages is detected on its main language and the switches are handled, so you do not pick anything before uploading.
What do I download, and who hears the Space?
TXT, DOCX, SRT, VTT and JSON. Space recordings are transcribed on our own servers and are never used for training. Send Spaces you hosted or have permission to use, not other people's rooms.
Related
More long talk recordings
Send the Space recording. The first 20 minutes cost nothing.
Transcribe my X SpaceOperated by Neugence Technology Pvt. Ltd. · contact@whipscribe.com · Security · Privacy · Terms