ElevenLabs released Music v2 today, a music-generation model that can switch genres mid-track and rebuild individual song sections via prompts. The model ships nearly 10 months after the startup launched the first version of its music-generation model, and it targets professional artists and marketing teams with section-level control over composition and vocals.
Music v2 can shift from opera to heavy metal and back within a single track, deliver fast rap without losing coherence, and layer non-musical sound effects into compositions. Artists can isolate a section of a generated song and regenerate it using text prompts without touching other parts of the track, a workflow shift from prior models that required full-track regeneration for any edit.
The model supports building songs section by section — intro, verse, chorus — then stitching them together, rather than generating short fixed-length clips. ElevenLabs said the model performs more reliably across languages, lyrics, vocals, and arrangements compared to Music v1.
Key facts
- 01ElevenLabs released Music v2 nearly 10 months after launching the first version of its music-generation model.
- 02The model can shift from opera to heavy metal and back, deliver fast rap without losing coherence, and add non-musical sound effects.
- 03Artists can select a section of a track and regenerate it via prompts without affecting other sections.
- 04The model is built on licensed data and cleared for commercial use, addressing copyright concerns that hit Suno and Udio with lawsuits.
- 05Music v2 is available on ElevenCreative and the new ElevenMusic platform, with ElevenAPI access coming soon.
The music-generation race has accelerated in recent months. Google, Stability AI, and Suno have all shipped new models with longer track support and more complex composition handling. At Google I/O, Google added cover creation, section-level editing, and music-video generation to its Flow Music tool.
ElevenLabs emphasized that Music v2 is built on licensed data and cleared for commercial use, a positioning move as Suno and Udio face copyright lawsuits over their training data. Striking licensing deals with labels has become table stakes for music-generation startups aiming at commercial markets.
Music v2 is available now on ElevenCreative, the company's tool for marketing and branding teams, and on the newly launched ElevenMusic platform for generating AI songs. ElevenAPI access is coming soon.
The section-level editing capability is the differentiator here. Prior AI music tools treated tracks as monolithic outputs — regenerate the whole thing or accept what you get. Music v2's prompt-based section replacement lets artists iterate on specific moments without resetting the entire composition, a workflow closer to traditional DAW editing than to prompt-and-pray generation.
The licensed-data positioning also matters. Suno and Udio's legal troubles have made enterprise buyers cautious about music-generation tools, particularly for commercial use cases like ads and branded content. ElevenLabs is betting that commercial clearance will win the marketing-team segment even if hobbyists don't care about licensing provenance.
The wild-card risk is whether section-level control actually improves creative outcomes or just adds friction. If the model's outputs are reliably high-quality end-to-end, artists may prefer full-track generation with fewer knobs. If they're inconsistent, section editing becomes the fix for a reliability gap, not a feature upgrade.
Working on something we should cover, or seeing a story we missed? Send leads, documents, or feedback to hello@aichatdaily.com. For sensitive tips, see our secure tips page for Signal and PGP options.
Spotted an error? Email hello@aichatdaily.com with the URL and the issue, or read our full corrections policy.
