Eleven Music v2.5

Audio modelCard summarized

Most advanced music model

● Re-checked 12 Oct 2026 · 34 facts · 0 corrections · 3 unconfirmedSource: Music v2.5 launch post and Eleven Music docs (no model card published)

Use it via API

$0.15 / min

Code example Compare

Where to call it

ElevenLabs APImusic_v2_5

Supports

No feature list in the maker's docs.

Full feature support

Good for

Music for film, TV, podcasts, social video, ads and games
Control over genre, style and structure via composition plans
Section-level edits (inpainting) without regenerating the whole song

Overview

ElevenLabs · 03Music

Music v2.5

Most advanced music model

Typical price

$0.15 / min

Music generation

Max length: 5 min
Languages: English, Spanish, German, Japanese and more
Modes: text-to-music, vocals or instrumental
Released: 11 Sep 2026

Music v2.5 is ElevenLabs' most advanced text-to-music model. It builds on Music v2 with improved audio quality and prompt adherence, and supports the same workflows: prompts, composition plans, Audio Reference and inpainting. ElevenLabs says songs sound more layered, with more natural-sounding instruments. launch post; music docs

music_v2_5

Typical price: $0.15 / min
Max length: 5 min
Languages: English, Spanish, German, Japanese and more
Weights: Closed
Released: 11 Sep 2026

text-to-music
vocals or instrumental
composition plans
audio reference
inpainting / section edits