ElevenLabs’ new music generation model can switch genres mid-track

Audio AI company ElevenLabs has launched a new version of its music generation model, called Music v2, that can switch genres mid-track. The company said the model is designed to handle the complexity of singing and composing. The new release comes nearly 10 months after the startup launched the first version of its music generation model.

ElevenLabs noted that the model can transition from opera to heavy metal and back, deliver fast rapping without losing cohesion, and add non-musical sound effects to the track. With the new model, artists can select a part of the song and recreate it using prompts without touching other parts of the track.

Additionally, instead of creating short clips, artists can create a song by sections, including intro, verse, and chorus, and then piece them together. ElevenLabs added that the model works more reliably across languages, lyrics, vocals, and arrangements.

In the past few months, AI labs have been racing to release models that can produce professional-grade music. Google, Stability AI, and Suno have also released new music generation models that have the capabilities of creating longer, more complex tracks. At the Google I/O developer conference, Google added the ability to easily create song covers, edit songs by sections, and create music videos with its Flow Music tool.

ElevenLabs stressed that the new model is built on licensed data and is licensed for commercial use, so users can use the routes freely. Closing deals with labels is key, given that other AI music startups, such as Suno and Udio, have faced court cases over copyright issues.

The new model is available on ElevenLabs’ ElevenCreative tool for marketing and brand teams, alongside ElevenMusic’s newly launched AI-generated song creation platform, with ElevenAPI coming soon.