ElevenLabs’s new music generation model can switch genres mid-track

Published: (May 27, 2026 at 10:14 AM EDT)
2 min read
Source: TechCrunch

Source: TechCrunch

Overview

Voice AI company ElevenLabs has launched Music v2, a new version of its music‑generation model that can switch genres mid‑track. The model is designed to handle both vocal and compositional complexity, allowing it to move from opera to heavy metal (and back), deliver fast rap without losing coherence, and add non‑musical sound effects to a track. Artists can select a part of a song and recreate it using prompts without affecting other sections.

Instead of generating short clips, Music v2 lets creators build a song by sections—intro, verse, chorus—and stitch them together. The model also performs more reliably across languages, lyrics, vocals, and arrangements.

Industry Context

In recent months, AI labs have been racing to release models capable of generating professional‑grade music:

These developments reflect a broader push toward more flexible and higher‑quality AI‑generated music.

ElevenLabs emphasizes that Music v2 is built on licensed data and cleared for commercial use, allowing users to freely incorporate generated tracks into their projects. Recent licensing agreements between major labels and streaming platforms—such as Universal Music Group’s renewal with TikTok and Spotify’s deals—highlight the importance of clear rights management for AI‑generated music.

Other AI music startups, including Suno and Udio, have faced copyright lawsuits, underscoring the significance of ElevenLabs’ approach to licensing.

Availability

Music v2 is currently available through ElevenLabs’ ElevenCreative tool, aimed at marketing and branding teams. It is also integrated into the newly launched ElevenMusic platform for creating AI‑generated songs. An API version (ElevenAPI) is slated for release soon.

0 views
Back to Blog

Related posts

Read more »