YouTrained

Report Gavacent built from the datasets alone

Yes. Gavacent has 5 videos listed in datasets used to train and test AI models.

This page only knows about the videos the datasets list. To check every upload on the channel:

Used for training and testing 5

videos in AudioSet

A list of about a million ten-second YouTube clips, each labelled with the sounds in it, that Google published in 2017. Labs use it to train and test general audio and music models.

Including The Last Story Music - Sad, The Last Story Music - Military, The Last Story Music - Sounds of the City

Used for testing 1

video in MusicCaps

A set of 5,521 ten-second music clips from YouTube, each with a written description, that Google published in 2023. It is the standard test set for text-to-music models.

Including The Last Story Music - Sad

AudioSet 5 videos, 5 rows

The Last Story Music - Military

Clip 30s to 40s · Open clip on YouTube · Labels: Music

youtube_video 1owDIL0D22Y · row unbalanced_train:1owDIL0D22Y:30:40

AudioSetunbalanced_train

The Last Story Music - Sounds of the City

Clip 30s to 40s · Open clip on YouTube · Labels: Music, Sad music, Tender music

youtube_video Sag-VcXevTM · row unbalanced_train:Sag-VcXevTM:30:40

AudioSetunbalanced_train

The Last Story Music - Memories

Clip 150s to 160s · Open clip on YouTube · Labels: Music, Ambient music

youtube_video tDuHiYOzzOY · row unbalanced_train:tDuHiYOzzOY:150:160

AudioSetunbalanced_train

The Last Story Music - Fragment

Clip 430s to 440s · Open clip on YouTube · Labels: Music, Sad music

youtube_video ueKwo5REHl8 · row unbalanced_train:ueKwo5REHl8:430:440

AudioSetunbalanced_train

MusicCaps 1 videos, 1 rows

The Last Story Music - Sad

“The Classical song features wide sustained strings and subtle mellow piano chords. It sounds sad and emotional - like something you would hear in the video games, as a background music for a sad scene.”

Clip 30s to 40s · Open clip on YouTube

youtube_video eZNnuRvrZDU · row eZNnuRvrZDU:30:40

MusicCaps

What this means

Last reviewed 2026-09-24.

Presence in a public research dataset shows that a clip of your recording was listed by academic or industry researchers as material for building or testing audio models. It does not by itself show which commercial products, if any, used the clip. The legal picture is moving. On 31 July 2026 the Regional Court of Munich I ruled in GEMA's case against Suno (case 42 O 763/25) that reproducing works for training, holding them in a model in retrievable form, and generating similar outputs can each infringe copyright under German and EU law; the judgment is not final and can be appealed. In the United States, Warner Music Group settled its claims against Suno on 25 November 2025 with a licensing deal, while the parallel claims by Universal and Sony were still pending at that point. Since then BMG (12 August 2026) and Believe/TuneCore (8 September 2026) have signed opt-in licensing deals with Suno.

What you can do

3 routes. None is a guarantee.

Keep a copy

Provenance

JSON export SHA-256 5101462a15e838753f79f7a2966498952798a541388b96b36d15c0f8e90b3a3c

Dataset versions indexed
DatasetFileRowsLoadedSHA-256
audiosetbalanced_train_segments.csv8,8362026-09-24T10:30:36+00:003b83e5ff9ed72cfd…
audioseteval_segments.csv7,8482026-09-24T10:30:36+00:00f7055f53935f70e7…
audiosetunbalanced_train_segments.csv1,063,3332026-09-24T10:30:43+00:00bb2dfd5e4f1ced39…
laion_disco_12mtrain-00000-of-00005.parquet2,464,1842026-09-24T12:18:19+00:00f8b1f0034f8f1e94…
laion_disco_12mtrain-00001-of-00005.parquet2,464,1832026-09-24T12:32:29+00:0071d78ad14ee3f85d…
laion_disco_12mtrain-00002-of-00005.parquet2,464,1832026-09-24T12:49:06+00:000feba570a0e8e73c…
laion_disco_12mtrain-00003-of-00005.parquet2,464,1832026-09-24T13:06:37+00:0021a77d99fd85ad2f…
laion_disco_12mtrain-00004-of-00005.parquet2,464,1832026-09-24T13:24:36+00:006ac5f59958b6b813…
musiccapsmusiccaps-public.csv5,5212026-09-24T10:29:42+00:008cc109ac507b5e5a…