Transcribe long recordings from a Sony Xperia Music Pro sessions and recorder files.
A long recording made on a Sony Xperia, whether in Music Pro or a recorder app, transcribes once you export the file and upload it here, and a 4-hour session comes back in about 8 minutes. The first 20 minutes are free, and two 4-hour recordings (480 minutes) fit the $6 pack of 500 minutes.
From the Xperia to the text
Good microphones make long recordings worth reading, not just keeping.
Exporting the file
Music Pro is built around music takes, so look in the project or track menu for an export or share option and check the export settings for the file type before you save it. A recorder app usually offers Share from its list of recordings. Send the file to Google Drive or your downloads folder, then use upload page.
Speech in, music out
WhipScribe transcribes what people say. Sung lyrics, instruments and backing tracks are not written out, so a rehearsal comes back as the talk between takes: the count-ins, the notes on tempo, the decision to drop the second verse. For an interview or a talk recorded on the phone, the whole conversation becomes text.
Hours on one pack
A 4-hour session is 240 minutes, just under half the $6 pack of 500. A weekly 3-hour rehearsal over three months, twelve sessions, makes 2,160 minutes and belongs on the $24 pack of 5,000. Thirteen 4-hour recordings across half a year come to 3,120 minutes, also on the $24 pack.
No link to Sony
There is no integration with Music Pro or with any Sony account, and no app to install on the phone. You decide which file leaves the device, and the transcript appears in your browser when it is done.
Long phone recordings elsewhere
A four-hour file is easy to make and hard to go back through.
✗ Left as audio
Hours of sound with the useful parts buried.
- Searching by ear for one comment
- Session notes written from memory
- OpenAI's Whisper API stops at 25 MB
- Large exports that will not send by message
- No notes on which take was kept
- Long takes nobody replays
✓ Exported and transcribed
The talk on the recording as text, by chapter.
- Roughly 8 minutes for a 4-hour file
- Two long sessions inside the $6 pack
- Chapters at each break
- Decisions on each song listed
- Chat to find a remark
- TXT and DOCX for notes
Sample
A long rehearsal recorded on an Xperia, as it comes back.
These lines are illustrative and were written for this page; they are not from a real session. Timestamps follow a 4-hour 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
Xperia recordings, the common questions.
How long does a 4-hour Xperia session take to process?
About 8 minutes, given roughly 2 minutes of processing per audio hour. On a slow connection the upload can take longer than the transcription itself.
Does WhipScribe write out the songs and instruments?
No. Only speech is written out; music, sound effects and crowd noise are skipped. A recording that is mostly playing returns only the spoken parts, which is often what you want from a rehearsal.
What file type does Music Pro export?
It depends on the app version and the export settings you choose, so check them before saving. Common audio files such as WAV, M4A, MP3 and FLAC all upload, and a video file works too.
How big can one file be?
The ceiling is 10 hours or 5 GB per file, whichever the recording reaches first. A high-resolution WAV is heavy: at 48 kHz and 24 bits in stereo it grows by about 1 GB an hour, so a 4-hour session approaches 4.2 GB. Before your first pack, uploads stop at 2 GB, so export a compressed copy or buy a pack first.
What does it cost?
First-time visitors get the first 20 minutes free; past that, a longer recording is previewed and a pack from $6 finishes it from where the preview ended. A 4-hour file then uses 240 of the 500 minutes in that pack, and credits never expire.
What can I download, and does Sony or anyone else see the file?
The downloads are TXT, DOCX, SRT, VTT and JSON, and nothing is shared with Sony. Files from your Xperia are transcribed on our own servers and never used for training.
Related
Other phone recordings
Export the recording from your Xperia. Your first 20 minutes of Xperia audio are free.
Transcribe my Xperia recordingOperated by Neugence Technology Pvt. Ltd. · contact@whipscribe.com · Security · Privacy · Terms