ElevenLabs Music v2 launched on May 26, 2026, enabling seamless mid track genre transitions and section by section 'inpainting' editing with far more complex vocals — but its biggest differentiator from Suno and Udio... The new inpainting feature lets users regenerate specific parts of a track without starting over,...

Create a landscape editorial hero image for this Studio Global article: How does ElevenLabs' newly launched Music v2 model enable mid-track genre switching, what new capabilities does it offer for section-by-sect. Article summary: ElevenLabs launched **Music v2** on May 26–27, 2026 — a new AI music generation model that can switch genres mid-track, edit songs section-by-section via "inpainting," and handle far more complex vocals and arrangements . Topic tags: general, general web, user generated. Reference image context from search candidates: Reference image 1: visual subject "All the latest in AI ‘music’. Its new Music v2 model can generate songs that can switch from opera to heavy metal mid-track, while handling faster rap delivery and non-musical soun" source context "ElevenLabs says its updated AI music generator can create genre ..." Reference image 2: visual subject "AI tried to
ElevenLabs released Music v2 on May 26, 2026, marking a significant step forward for AI-generated music . The new model introduces two headline capabilities: the ability to switch musical genres mid-track without losing coherence, and granular "inpainting" controls that let users regenerate specific sections of a song. These features arrive alongside a pricing model that spans free hobbyist access to enterprise-only tools, all built on a foundation of licensed training data that deliberately avoids the legal battles plaguing competitors like Suno and Udio.
Music v2 can seamlessly transition between radically different genres within a single composition. ElevenLabs demonstrated transitions from opera to heavy metal and back again, as well as moves from country to fast rap, without any break in flow .
This is not just a parlor trick. The underlying model has received broad improvements to vocal clarity, instrumental quality, and arrangement coherence . It can deliver rapid, intelligible rap vocals and even incorporate non-musical sound effects directly into a track
. In practice, this means artists can now construct a song section by section — setting an intro in one style, a verse in another, and a chorus in a third — using natural language prompts to define the genre and mood for each segment.
The most consequential new production feature is music inpainting. Instead of regenerating an entire song to fix a 10-second bridge, users can now select a specific section and recreate just that part using a text prompt .
According to ElevenLabs' documentation, the workflow involves generating a track, storing it, and then referencing its sections in new "composition plans." You can regenerate a weak verse, extend a track with a new intro or outro, or even combine sections from multiple stored songs .
There is a significant catch: music inpainting is currently an enterprise-only feature. Access requires contacting ElevenLabs' sales team directly . For individual creators and smaller teams, the editing experience is more limited, though the core Music v2 model improvements in quality and genre control apply to all tiers.
Music v2 powers three distinct ElevenLabs products :
On the core ElevenLabs platform, Music v2 access is available across all subscription tiers :
Alongside the v2 launch, ElevenLabs cut pricing for both Music v1 and v2 by up to 50% for API customers and up to 40% for ElevenCreative self-serve users .
While Music v2's creative features grab headlines, the real strategic difference is legal. ElevenLabs entered the AI music space in August 2025 with a fundamentally different approach to training data .
Before ever launching a music product, the company secured licensing deals with Merlin Network (representing thousands of independent labels) and Kobalt Music Group (a major publishing rights organization) . It also built a data pipeline of 14 million pre-cleared songs through SourceAudio
. Under these agreements, artists must opt in for their music to be used in AI training
. This means ElevenLabs users can generate tracks with a clear chain of commercial rights from day one.
The contrast with Suno and Udio is stark. Both startups were sued in June 2024 by the Recording Industry Association of America (RIAA) on behalf of Universal Music Group, Sony Music Entertainment, and Warner Music Group for allegedly training on copyrighted recordings without permission . The litigation has reshaped the competitive landscape
:
Suno and Udio have effectively admitted in court filings that they trained on unlicensed copyrighted recordings . Both are now working their way out of infringement exposure through settlements and licensing deals, but the process is ongoing.
ElevenLabs' pre-clearance approach gives it a distinct advantage for commercial users — brands, advertisers, and developers — who need unambiguous legal coverage for AI-generated music. As CEO Mati Staniszewski described it, the licensing deals create "legal cover for broad commercial use" . That enterprise-safe positioning, combined with the new creative capabilities in Music v2, represents the company's core bet on where the AI music market is heading.
Studio Global AI
Use this topic as a starting point for a fresh source-backed answer, then compare citations before you share it.
ElevenLabs Music v2 launched on May 26, 2026, enabling seamless mid track genre transitions and section by section 'inpainting' editing with far more complex vocals — but its biggest differentiator from Suno and Udio...
ElevenLabs Music v2 launched on May 26, 2026, enabling seamless mid track genre transitions and section by section 'inpainting' editing with far more complex vocals — but its biggest differentiator from Suno and Udio... The new inpainting feature lets users regenerate specific parts of a track without starting over, though it is currently limited to Enterprise customers who contact sales.
Pricing starts with a free tier and scales to a $6/month Starter plan for commercial rights; API access is priced around $0.50 per minute of generated audio.