Elevenlabs makes Music v2.5 available via app and API with free and pro tier options

| Source: THE DECODER

Tags: ElevenLabs, AI music generation, Music v2.5, Universal Music Group, audio AI, API

ElevenLabs releases Music v2.5, which beat its predecessor in 47,885 blind preference tests across R&B, Soul, Hip-Hop, Rock, and orchestral genres — now available via API with a free tier (5 lossless downloads/day) and Pro tier (400/month), trained on licensed music.

Details

ElevenLabs has updated its AI music generator with Music v2.5, backed by the strongest listening evidence the company has yet published: 47,885 pairwise comparisons in which listeners preferred the new version, particularly for R&B, Soul, Hip-Hop, Rock, and orchestral styles. The company says generated songs now sound 'fuller and more natural,' and that users retain rights to their output. Access is tiered: free accounts get five lossless track downloads per day, while Pro subscribers receive 400 per month. Commercial use is allowed depending on industry and purpose, but free-tier tracks require attribution. The model blocks downloads of covers of specific artists' songs and prohibits style imitation — positioning ElevenLabs as more rights-protective than some rivals. Music v2.5 is also now accessible through the ElevenLabs API, enabling programmatic music generation for developers and product teams. The older v2 model remains available. ElevenLabs recently signed a deal with Universal Music Group, but clarifies it applies only to future, separate products — not Music v2.5, which was trained on what the company calls 'licensed stems and music' without further disclosure. That licensing distinction matters in context: Suno is currently facing lawsuits over allegedly training on copyrighted material without consent. ElevenLabs' more cautious approach may give it an advantage in enterprise and licensing-sensitive markets, though the lack of specifics around its training data leaves some questions open.