How do you convert MKV to MP3 for transcription? One command, or one VLC menu.
Run ffmpeg -i recording.mkv -vn -c:a libmp3lame -b:a 96k recording.mp3, or in VLC use Media, Convert/Save, pick an audio MP3 profile and start; menu labels differ a little between VLC versions. A 4-hour MKV of around 11 GB becomes an MP3 of about 173 MB, which uploads in minutes and is transcribed in roughly 8 minutes.
Converting MKV, step by step
MKV is a container, not a sound format. Converting just lifts out the speech.
Where long MKV files come from
OBS Studio has long offered MKV as its crash-safe recording format, and many screen recorders, stream archivers and video downloaders save to it too. That is why the longest files people hold, a full stream or a day of screen capture, are so often .mkv.
The ffmpeg way
ffmpeg -i recording.mkv -vn -c:a libmp3lame -b:a 96k recording.mp3. The -vn flag drops the picture and 96 kbps is plenty for speech. If the MKV carries several audio tracks, such as a microphone and desktop sound, add -map 0:a:0 to choose the first one, or -map 0:a:1 for the second.
The VLC way
Open VLC, choose Media, then Convert/Save, add the MKV, press Convert/Save, choose an MP3 audio profile and set a destination file. On a Mac the same tool sits under File, Convert / Stream. A 4-hour file can take a while in VLC because it decodes the whole thing.
Then send it
Drop the MP3 in the box on this page if it is under 500 MB, or use the upload page for anything larger, up to 10 hours or 5 GB. The transcript returns with timestamps, a brief, chapters, the names and numbers spoken and a chat over the text.
Why convert at all
A long MKV is mostly picture. The words are a few percent of the file.
✗ Uploading the MKV
Video-heavy MKV files are slow to move and not every uploader reads them.
- About 2.7 GB an hour at 6 Mbps
- A 4-hour stream near 11 GB
- Over the 5 GB line for one file
- A browser that may not list .mkv
- Two audio tracks, one picked at random
- An evening spent uploading
✓ Uploading the MP3
Strip the picture and the same recording is a fraction of the size.
- About 43 MB an hour at 96 kbps
- Four hours in roughly 173 MB
- The chosen audio track, on purpose
- Same length, so same timestamps
- About 8 minutes to a transcript
- Exports in five formats
Sample
A long screen-recorded tutorial, converted from MKV.
Illustrative lines written for this page; no real recording or person. Times match the original MKV.
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 $4 (300 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
$4/300 min
5 hours of audio — $0.80 an hour. One-time — credits never expire.
- 300 minutes of audio
- All export formats
- AI chat over the whole transcript
- Executive summary & key quote
Best value
$18/3,000 min
50 hours of audio — $0.36 an hour. Credits never expire.
- 3,000 minutes of audio
- Summary, chapters and key quotes
- All export formats
- AI chat over the whole transcript
Bulk pack
$32/6,000 min
100 hours of audio — $0.32 an hour. Credits never expire.
- 6,000 minutes of audio
- Summary, chapters and key quotes
- API access for batch pipelines
- All export formats
FAQ
MKV to MP3, answered.
Do I have to convert the MKV?
Not always. Most files upload as they are, up to 10 hours or 5 GB. Try the MKV first; if the browser will not offer it or the upload refuses it, convert it. Converting also makes sense when the MKV is over 5 GB or longer than 10 hours.
Is there a faster command that does not re-encode?
If the audio in the MKV is AAC, ffmpeg -i in.mkv -vn -c:a copy out.m4a copies it out in seconds with no quality change. Run ffprobe in.mkv to see the audio codec; if it says opus or something else, use the MP3 command instead.
Which audio track should I pick?
Recorders that split microphone and desktop sound into separate tracks put the voice on one of them. Listen to a minute of each with VLC's Audio, Audio Track menu, then map that one in ffmpeg. The transcript can only hear the track you send.
What will a month of recordings cost?
Eight 4-hour sessions are 1,920 minutes, which fits the $18 pack of 3,000 minutes with 1,080 left. One 4-hour file alone is 240 minutes, inside the $4 pack of 300 minutes. The opening minutes are a free preview.
The stream is on Twitch or YouTube already. Do I need the MKV?
No. Paste the Twitch, Kick or YouTube link and nothing is uploaded. Stream recordings over 6 hours start once a pack is on the account.
Languages, formats and privacy?
99 languages are detected automatically. Exports: TXT, DOCX, SRT, VTT and JSON. Recordings are transcribed on our own servers and are never used for training.
Related
Related pages
Convert it, then drop it here. The opening minutes come back free.
Transcribe my MP3Operated by Neugence Technology Pvt. Ltd. · contact@whipscribe.com · Security · Privacy · Terms