ElevenLabs · 2026-05-26 · major
ElevenLabs Music v2 — New Music Model Switches Genres Mid-Track, Adds Section-Level Inpainting, and Cuts API Prices Up to 50%
ElevenLabs' new music model shifts genres mid-song, regenerates any section of a track without touching the rest, and embeds sound effects. It powers ElevenMusic, ElevenCreative, and the API, with prices cut up to 50%.
A music model that swaps genres mid-track and regenerates just one section of a song.
Key specs
| Eleven api price cut | up to 50% |
|---|---|
| Eleven creative price cut | up to 40% |
What is it?
Music v2 is ElevenLabs' latest text-to-music model. You describe a song in plain language and it generates full tracks with vocals, instrumentation, and arrangement. It is the engine behind the ElevenMusic app, the ElevenCreative tool, and the music API.
How does it work?
The model builds songs section by section — intro, verse, chorus — while keeping the whole track coherent, so a single song can move from opera to heavy metal and back or sustain dense, fast rap. An inpainting mode lets you select any segment and regenerate just that part from a prompt, leaving the rest untouched, and non-musical sound effects can be embedded inline. It is trained only on licensed data cleared for commercial use.
Why does it matter?
Mid-track control and section-level inpainting let creators revise part of a song without regenerating the whole thing. Training only on licensed data cleared for commercial use gives commercial users a clearer legal footing, and API price cuts of up to 50 percent lower the cost of generating audio at scale.
Who is it for?
musicians, content creators, marketing teams
Try it
https://elevenlabs.io/music