ElevenLabs Unveils Music v2: AI Music Generation with Mid-Track Genre Switching
New Model Offers Enhanced Complexity, Cross-Language Reliability, and Commercial Clearance
ElevenLabs has unveiled Music v2, an advanced AI music generation model capable of switching genres mid-track, handling complex vocals and compositions, and allowing artists to edit songs by sections without affecting other parts. This launch comes nearly 10 months after the company’s first music-generation model. Music v2 can seamlessly transition from opera to heavy metal and back, deliver fast, coherent rap, and incorporate non-musical sound effects. Artists can now recreate specific song sections using prompts and build tracks section by section (intro, verse, chorus) before stitching them together. The model also performs more reliably across languages, lyrics, vocals, and arrangements.
The AI music generation space has seen intense activity recently, with Google, Stability AI, and Suno also releasing models capable of generating longer, more complex tracks. At Google I/O, Google showcased updates to its Flow Music tool, including easy cover creation, section-based editing, and music video generation. ElevenLabs highlights that Music v2 is built on licensed data, cleared for commercial use, allowing users to freely utilize generated tracks—a key point given that startups like Suno and Udio have faced legal challenges over copyright.






