Skip to main content
Back to News
Product
2 min read
GB

ElevenLabs launches Music v2 model with in-track style switching capability.

The AMW Read

Incremental product update in generative media segment; extends known player's offering but does not resolve an open debate or reshape segment structure.
NoveltySignificance
Multimodal · Player Map

ElevenLabs launches Music v2 model with in-track style switching capability.

ElevenLabs has released version 2 of its music generation model, adding the ability to switch musical styles within a single track — a feature that moves beyond static, one-style-per-generation tools and toward more dynamic compositional control. The update builds on ElevenLabs' existing text-to-music offering, positioning the company deeper into generative audio for content creators and producers.

This matters because ElevenLabs is expanding its product surface area from speech synthesis into full music generation, a natural adjacency in the generative media substrate. The in-track style switch capability differentiates it from earlier text-to-music tools that generated fixed clips, bringing the product closer to usable creative workflows. The move also intensifies competition with companies like Suno and Udio, which have dominated the AI music segment since mid-2023 but lack ElevenLabs' existing distribution via its 10M+ user base and API ecosystem. ElevenLabs is effectively applying a 'context-engineering moat' pattern to music — turning raw model output into controllable, editable audio.

The strategic read: ElevenLabs is signaling it wants to own the entire 'voice-to-music' pipeline, not just synthetic speech. Music v2's style-switching is a counter to the 'fastest-ARR-ramp' pattern that Suno rode to tens of millions in revenue, but with a more productized, developer-friendly layer. If ElevenLabs can wrap Music v2 in its existing API and licensing architecture — the same acqui-licensing playbook that won it publishing deals — it could become the infrastructure layer for AI-generated music in video, gaming, and social apps, not just another standalone app. The open question is whether music copyright holders will react differently than they did to speech synthesis, given the asset class's litigious history.

#ElevenLabs #MusicGeneration #GenerativeMedia #AIProduct #TextToMusic #CreativeTools

#ElevenLabs#Music v2#AI music generation#style switching

How This Connects

Based on Multimodal · Player Map

  1. 1d agoMartin Scorsese endorses AI tools in film pre-production, joining Black Forest Labs (블랙 포레스트 랩스) as...
  2. 1w agoElevenLabs launches Music v2 model with in-track style switching capability. · THIS ARTICLE
  3. 3w agoElevenLabs raises Series D at $11B valuation, led by Sequoia Capital, with Andreessen Horowitz and I...ElevenLabs
  4. 1mo agoOpenAI launches GPT Image 2.0 with integrated text-image generation for commercial designOpenAI
  5. 1mo agoOpenAI sets April 26, 2026 discontinuation date for Sora video generation productOpenAI
  6. 1mo agoOpenAI has officially announced the release of ChatGPT Images 2.0, integrating the new image generat...OpenAI

Related News

More news from ElevenLabs

Stay updated with the latest news and announcements from ElevenLabs.

View all ElevenLabs news

Discover AI Startups

Explore 2,000+ AI companies with VC-grade analysis, funding data, and investment insights.

Explore Dashboard