Transcribe a long AV1 video file the talk inside a modern codec.
Packs start at $4 for 300 minutes, and credits never expire. A 1080p AV1 file is often 0.5 to 2 GB an hour, so a long one can pass the 5 GB line; then extract the audio track, which is a few dozen megabytes an hour.
AV1 and the transcript
The transcript only needs the soundtrack. AV1 is about the picture, so the real question is the file around it.
Where long AV1 files come from
AV1 is the royalty-free video codec that newer screen recorders, streaming software and some phones and cameras can encode, and that video sites deliver to modern browsers. A long AV1 file is usually a stream recording, a screen capture of a training session, or a downloaded talk, wrapped in MP4, WebM or MKV.
Gigabytes per hour
AV1 compresses well, but the bitrate is set by whoever recorded it. A 1080p screen recording at around 2 to 4 Mbps is roughly 0.9 to 1.8 GB an hour; 4K can be several times that. The audio inside, usually Opus or AAC, is a small part of the total.
Uploading, or sending the sound
An AV1 MP4 or WebM can go up as it is. The box on this page takes up to 500 MB, and a larger file continues on the upload page, up to 5 GB with or without a pack. If the upload refuses the file or it is too big, convert to MP3 or MP4 with ffmpeg or VLC; ffmpeg -i talk.mkv -vn -b:a 96k talk.mp3 keeps only the sound.
Links instead of files
If the AV1 video is already on YouTube, Vimeo, Twitch or Kick, or in a Google Drive share, paste the link instead of downloading it; there is no upload at all. Stream recordings over 6 hours start once a pack is on the account.
Long video, the hard way
Video files grow faster than the patience it takes to watch them back.
✗ A file too large to share
Hours of AV1 video hit upload caps, and playback on older machines stutters.
- Players that cannot decode AV1
- Uploads that time out after an hour
- Re-encoding the whole video for no reason
- Scrubbing for the one explanation
- Captions typed line by line
- Notes that never match the timeline
✓ Sound in, text out
Upload the video, the extracted audio, or a link; the whole session comes back as text.
- Four hours in about 8 minutes
- Chapters with timestamps
- SRT and VTT captions
- Questions the session answers
- A chat over the transcript
- Minutes that keep for the next one
Sample
Hour three of a recorded training stream.
Illustrative lines written for this page, not a real stream. Times match a long AV1 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 $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
Long AV1 videos: questions
Does the upload accept AV1 video?
An AV1 file in MP4 or WebM usually uploads as it is, since the transcript is made from the sound. If the upload refuses it, for example an MKV, convert to MP3 or MP4 with ffmpeg or VLC, or extract only the audio.
My recording is over 5 GB. What now?
Extract the audio. At 96 kbps, sound alone is about 43 MB an hour, so even ten hours is around 430 MB and fits the box on this page. Before the first pack, files up to 5 GB upload.
How long does a four-hour stream take?
About 8 minutes after the upload, at around 2 minutes per audio hour. A public run of 9.31 hours took 1,033 seconds.
What does a month of streams cost?
Four streams of 4 hours is 16 hours, or 960 minutes, on the $18 pack (3,000 minutes). Packs start at $4 for 300 minutes, and credits never expire.
Can I get captions for the video?
Yes. SRT and VTT exports carry the timestamps, so they line up with the original AV1 video when you add them back. TXT, DOCX and JSON are there too.
Languages and privacy?
99 languages are detected from the speech, and music and game sound are not transcribed, only voices. Recordings are transcribed on our own servers and are never used for training.
Related
Other long video formats
A long AV1 recording. The talk as text in minutes.
Transcribe my AV1 videoOperated by Neugence Technology Pvt. Ltd. · contact@whipscribe.com · Security · Privacy · Terms