OPEN LINK ↗
// 10h agoMODEL RELEASE
ElevenLabs launches Music v2 for creators
ElevenLabs has released Music v2, a new music generation model that improves vocals, instrumentation, arrangement, and multilingual output. The model supports longer, section-by-section composition, inpainting to regenerate specific parts of a track, and more complex shifts within a song without losing coherence. It powers ElevenMusic and ElevenCreative now, with ElevenAPI access coming soon, and is trained on licensed data for commercial use.
// ANALYSIS
Hot take: this is a meaningful step from “generate a clip” toward “produce an editable song,” which is where AI music starts feeling usable for real workflows rather than demos.
- –The biggest upgrade is control: section-level composition and inpainting make iteration much more practical.
- –Multilingual and vocal improvements matter because they attack the most obvious failure modes in AI music.
- –ElevenLabs is clearly positioning this as a platform release, not just a model drop, with separate surfaces for creators, developers, and brands.
- –The licensed-data angle is strategically important; music generation lives or dies on rights clarity as much as quality.
// TAGS
elevenlabsmusic-v2audio-genmultilingualvocalslicensed-data
DISCOVERED
10h ago
2026-05-28
PUBLISHED
10h ago
2026-05-28
RELEVANCE
9/ 10
AUTHOR
toolfolio