ElevenLabs · Full songs, commercial-cleared, edited section by section.

ElevenLabs Music v2

Licensed AI music you can actually edit

ElevenLabs Music v2 generates complete studio-quality songs — vocals, instrumentation, and arrangement — trained only on licensed data and cleared for commercial use. Regenerate any verse, chorus, or bridge without touching the rest.

10 min
Max length (API)
70+
Genres
4
Downloadable stems
100%
Licensed training data
What's new

Licensed AI music you can actually edit

01

Trained on licensed data

Built exclusively on licensed music through deals with Merlin and Kobalt, so every track is cleared for commercial use — no sync fees, no clearance delays.

02

Section-by-section inpainting

Select any part of a track and regenerate just that section. Rework the bridge without touching the chorus, or rebuild an intro from a prompt.

03

Mid-track genre switching

Shift genres inside a single song — opera to metal and back in a handful of bars — while keeping vocals and structure coherent.

04

Multilingual vocals

Generate sung vocals with custom lyrics in English, Spanish, German, Japanese and a growing list of languages, or produce instrumental-only tracks.

Overview

Model at a glance

ElevenLabs Music v2 is the second generation of ElevenLabs' AI music model, released in late May 2026 under the Eleven Music product. From a text prompt it generates a complete song — vocals with custom lyrics, instrumentation, and full arrangement — or an instrumental-only track. Its defining trait among major AI music tools is that it is trained exclusively on licensed catalog data, secured through partnerships with the independent-label alliance Merlin and publisher Kobalt, which makes generated tracks cleared for commercial use on paid plans.

Beyond raw generation, v2 focuses on control and editability. Improved inpainting lets creators regenerate any single section of a track — a verse, chorus, or bridge — without disturbing the rest, and the model can switch genres mid-song while keeping vocals and structure coherent. It supports multilingual vocals, embedded non-musical sound effects, and stem separation for downstream mixing. The model is available in the ElevenLabs app and, for paying subscribers, through the Eleven Music API.

Model
ElevenLabs Music v2
Product brand
Eleven Music
Developer
ElevenLabs
Type
Text-to-music generation
Vocals
Multilingual, custom lyrics or instrumental
Max length
Up to 10 min (API); ~5 min (app)
Licensing
Trained on licensed data; commercial-cleared on paid plans
Access
ElevenLabs app + Eleven Music API
Capabilities

Key features

Full-song generation with vocals

From a single text prompt, Music v2 produces a complete track with sung vocals, instrumentation, and arrangement. You can supply your own lyrics or let the model write them, and generate instrumental-only versions when no vocals are needed.

Section-by-section inpainting

The upgraded inpainting engine lets you highlight any region of a track and regenerate only that part. Rework a weak bridge, swap a chorus melody, or rebuild the intro while the rest of the song stays exactly as it was.

Mid-track genre switching

A signature capability of v2: the model can transition between genres within a single song — for example moving from opera to metal and back over a few bars — while maintaining vocal coherence and structural continuity.

Multilingual vocals

Music v2 sings in multiple languages including English, Spanish, German, and Japanese, with a growing roster of supported languages. Lyrics and pronunciation are handled per language rather than transliterated.

Licensed, commercial-cleared output

Because the model is trained only on licensed data via Merlin and Kobalt agreements, tracks generated on paid plans are cleared for commercial use without separate sync licensing. Free-tier output carries usage restrictions.

Stem separation and export

Downloads can be delivered as a full mix, split into vocals and instrumentals, or separated into individual stems, giving producers material to remix, master, or drop into a DAW.

Tempo, key, and structural control

Creators can steer tempo and musical key and compose a song section by section — building verse, chorus, and bridge independently — for tighter control than a single one-shot generation allows.

Specs

Technical specifications

Generation

ModelElevenLabs Music v2
InputText prompt (+ optional custom lyrics)
OutputVocal songs or instrumental tracks
Max lengthUp to 10 minutes (API); ~5 minutes (app)
Minimum length~3 seconds

Editing & control

InpaintingRegenerate individual sections
Genre switchingMid-track transitions supported
StructureSection-by-section composition (verse/chorus/bridge)
ControlsTempo, key, prompt-guided regeneration
Sound effectsNon-musical SFX can be embedded

Output & licensing

VocalsMultilingual (English, Spanish, German, Japanese, +more)
StemsFull mix, vocals/instrumental split, or 4 stems
Training dataLicensed only (Merlin, Kobalt)
Commercial useCleared on paid plans; restricted on free tier

Access

InterfacesElevenLabs app; Eleven Music API
API accessPaid subscribers
ReleasedMay 2026
In practice

Use cases

Commercial video and ad soundtracks

Because paid-plan output is cleared for commercial use, marketers and video editors can score ads, product videos, and brand content without chasing sync licenses or worrying about takedowns.

Content creator background music

YouTubers, podcasters, and streamers can generate custom, on-brand tracks in the length and mood they need, then regenerate sections that don't quite fit rather than starting over.

Songwriting and demo drafting

Musicians can sketch full songs with vocals and lyrics, iterate on a specific verse or chorus via inpainting, and export stems to finish the production in their own DAW.

Games and interactive media

Developers can produce genre-flexible tracks — including mid-track transitions for shifting scenes — and pull stems for adaptive, layered audio systems.

Multilingual and localized releases

Teams releasing content across markets can generate vocal tracks in several languages from the same creative direction, keeping tone consistent while localizing the lyrics.

Generational leap

Music v2 vs. Music v1

Music v2 is a broad quality and control upgrade over the first Eleven Music model, adding mid-track genre switching and much stronger section editing.

FeatureElevenLabs Music v1ElevenLabs Music v2NEW
ReleasedAug 2025May 2026
Vocal & arrangement qualityStrongBroad quality jump
Section inpaintingBasicImproved, prompt-guided per section
Mid-track genre switchingNot featuredYes
Multilingual vocalsSupportedImproved, more languages
LicensingLicensed data, commercial-clearedLicensed data, commercial-cleared
Honest look

Current limitations

Commercial rights depend on your plan

Full commercial clearance applies to paid tiers (from the Starter plan up). On the free plan, commercial use is heavily restricted or removed, so read the plan terms before deploying tracks publicly.

API rollout and access

The Eleven Music API is available to paying subscribers, and v2 API access rolled out after the app. Availability of specific v2 endpoints and features can vary by plan and region.

Length and format constraints

Maximum track length differs between the app (~5 minutes) and the API (up to 10 minutes), and very long, highly structured compositions may need section-by-section assembly rather than a single generation.

AI music is still evolving

As with all generative music, output quality varies by prompt and genre, and complex vocal or lyrical requests may need several iterations. A higher-tier Eleven Music Pro model was announced as a later release.

FAQ

Frequently asked questions

Is ElevenLabs Music v2 cleared for commercial use?
Yes, on paid plans. The model is trained exclusively on licensed data through deals with Merlin and Kobalt, so tracks generated on the Starter plan and above are cleared for commercial use. Free-tier output carries usage restrictions, so check your plan before deploying a track commercially.
Can Music v2 generate vocals and lyrics?
Yes. It generates full songs with sung vocals from your own lyrics or lyrics it writes, in multiple languages including English, Spanish, German, and Japanese. It can also produce instrumental-only tracks.
How long can generated tracks be?
Track length is configurable. The Eleven Music API supports lengths up to roughly 10 minutes, while the app caps generations at about 5 minutes. Minimum length is around 3 seconds.
What is inpainting in Music v2?
Inpainting lets you select a specific section of a track — such as a verse or bridge — and regenerate only that part from a prompt, without changing the rest of the song. It's the main way to iterate without starting over.
Can I download individual stems?
Yes. Downloads can be delivered as a full mix, split into vocals and instrumentals, or separated into individual stems, which is useful for remixing or finishing a track in a DAW.
How is Music v2 different from Suno or Udio?
The key distinction is licensing: ElevenLabs Music v2 is trained only on licensed catalog data via Merlin and Kobalt agreements, which it positions as commercial-safe. It also adds mid-track genre switching and section-level inpainting for finer editing control.
Can I use ElevenLabs Music v2 on SharkFoto?
ElevenLabs Music v2 support on SharkFoto is coming soon. In the meantime you can use SharkFoto's currently available AI creative tools, and check back here for availability updates.

ElevenLabs Music v2 is Coming to SharkFoto

We're adding ElevenLabs Music v2 as platform access opens — explore SharkFoto's available AI tools today and check back for availability.

Try ElevenLabs Music v2 now