ElevenLabs announced the launch of Music v2, a new AI music-generation model that delivers significant improvements in vocals, instrumentation, arrangement quality, multilingual support, and creative control while expanding capabilities for musicians, developers, and brands.
Music v2 powers three of the company’s platforms: ElevenMusic, which enables users to listen, remix, and create tracks; ElevenAPI, which allows developers to integrate music generation directly into their products; and ElevenCreative, which provides downloadable music for advertising, branded content, and video production.
The new model introduces several enhancements over Music v1, including the ability to handle more sophisticated vocal performances and musical compositions. According to ElevenLabs, Music v2 can seamlessly transition between dramatically different genres within a single song while maintaining coherence throughout the composition.
The platform also features improved inpainting capabilities, allowing users to regenerate individual sections of a track without affecting the rest of the composition. This gives creators greater precision when refining specific elements of a song.
Another major addition is expanded song-building functionality. Rather than generating short clips, users can construct complete songs section by section, including intros, verses, choruses, and additional segments while maintaining continuity and structure across the entire composition.
ElevenLabs said Music v2 also delivers stronger multilingual performance, enabling lyrics, vocals, and arrangements to more reliably reflect the language in which users create their music.
For musicians and creators, ElevenMusic serves as a music production environment where users can begin with lyrics, moods, or reference tracks and develop them into complete compositions. Developers can access Music v2 through ElevenAPI to generate, edit, and reference-match music programmatically. Meanwhile, brands and content teams can use ElevenCreative Music to generate licensed music by specifying creative requirements such as mood, genre, tempo, and brand voice.
Alongside the launch, ElevenLabs announced price reductions of up to 50% for ElevenAPI customers and up to 40% for self-serve ElevenCreative customers.
The company noted that Music v2 is trained exclusively on licensed data and is cleared for commercial use, allowing customers to deploy generated tracks without sync fees, clearance delays, or usage restrictions.
KEY QUOTES:
“Music v2 delivers better vocals, instrumentation, and arrangement across every genre, with improved multilingual support and a set of new capabilities.”
“A single song can move from opera to heavy metal and back, sustain fast rap and dense lyrical delivery, and embed non-musical sound effects directly within the track, all without breaking musical coherence.”
“Music v2 also gives you granular control for how you work with the model. With improved inpainting, you can select any section of a track and regenerate just that part, tweaking the bridge without touching the chorus, leaving everything else exactly as it is.”
“Composition can now go further too. Rather than generating short clips, Music v2 lets you build a full song section by section — intro, verse, chorus, and beyond — maintaining structure and continuity throughout.”
“The model is trained only on licensed data and cleared for commercial use, so every track you generate is yours to use — no sync fees, no clearance delays, no restrictions on how you deploy it.”
Imogen Mulliner, Author, ElevenLabs
