2.7 billion parameters produce a complete piece of music in 6 minutes and 20 seconds—will bedroom producers soon become bedroom symphony orchestras?

View Original
MeNews
Stability AI releases the audio model Stability Audio 3.0, capable of generating professional-grade songs up to 6 minutes long
AIMPACT News, May 21 (UTC+8), Stability AI launched the Stability Audio 3.0 audio generation model family, consisting of four different specifications, with parameters ranging from 459 million to 2.7 billion. The small models focus on device-side operation and can generate audio within two minutes locally; medium and large models support creating complete music over 6 minutes and 20 seconds. (Source: AiHot)
This page may contain third-party content, which is provided for information purposes only (not representations/warranties) and should not be considered as an endorsement of its views by Gate, nor as financial or professional advice. See Disclaimer for details.
  • Reward
  • Comment
  • Repost
  • Share
Comment
Add a comment
Add a comment
No comments
  • Pinned