ElevenLabs Launches Music v2 With Better Vocals and 50% Price Cut.

ElevenLabs announced on LinkedIn the launch of Music v2, a significant upgrade to its AI music generation model that promises better vocals, instrumentation, and arrangement across every genre. The release includes a pricing cut of up to 50% for self-serve customers on ElevenCreative and ElevenAPI.

The updated model delivers several technical improvements that expand what developers and creators can generate. Music v2 now handles fast rap and dense lyrical delivery, two areas where previous AI music models have struggled to maintain clarity and rhythm. The system can also execute mid-track genre transitions, letting users shift from, say, jazz to electronic within a single composition.

Another addition is the ability to embed non-musical sound effects directly into tracks. This feature allows creators to integrate ambient sounds, voice samples, or other audio elements without requiring separate post-production steps.

Multilingual generation has been improved, and the model now supports long-form composition through a section-by-section workflow. Instead of generating an entire song in one pass, users can build tracks incrementally, refining verses, choruses, and bridges independently.

Music v2 powers three ElevenLabs products: ElevenMusic, ElevenAPI (coming soon), and ElevenCreative. Each platform is designed for a different use case. ElevenMusic serves individual artists and creators, ElevenAPI provides programmatic access for developers, and ElevenCreative targets brands and commercial production workflows.

The company cut pricing for Music generation by up to 50% across ElevenCreative and ElevenAPI self-serve tiers. This positions ElevenLabs more competitively against other AI audio tools, especially for developers integrating music generation into apps or services.

According to the official blog post, Music v2 is trained exclusively on licensed data and cleared for commercial use. This addresses a common concern among creators about the legal risks of AI-generated content.

ElevenLabs has been expanding rapidly across several product lines. The company recently launched Speech Engine to turn chat agents into voice agents with a single prompt, and partnered with the Stan Lee Universe to bring the comic legend's voice to its platform. In education, the company launched an Einstein voice agent and offered free Pro access to professors.

Music v2 represents a shift toward longer-form, more complex audio generation. While voice synthesis has been ElevenLabs' core strength, music generation opens a new revenue stream and competes more directly with platforms like Suno and Udio.

The section-by-section composition workflow is particularly notable. Most AI music tools generate complete tracks in one shot, which limits creative control. By letting users build songs incrementally, ElevenLabs gives creators a workflow closer to traditional digital audio workstations, where individual elements are layered and refined.

For solo creators and small teams, the 50% price cut makes AI-generated music more accessible for projects with tight budgets. The ability to generate multilingual tracks without switching tools or models simplifies workflows for international content.

Developers integrating music generation into apps via ElevenAPI will benefit from the improved vocal clarity and genre flexibility. The mid-track transition feature could be useful for adaptive music systems in games or interactive media, where the soundtrack needs to respond to user actions.

Brands using ElevenCreative for commercial production now have more control over sound design, thanks to the inline sound effects feature. This reduces the need for separate audio editing software and speeds up production timelines.

Music v2 is available now across all three platforms, with API access rolling out soon.