Voice AI company Eleven Labs launched a new version of the music generation model, called Music v2, that can switch genres mid-track. The company said the model is designed to handle both vocal and compositional complexity. The new release comes nearly 10 months after the startup introduced the first version of the music generation model.
ElevenLabs noted that the model can go from opera to heavy metal and back, deliver fast rap without losing coherence, and can add non-musical sound effects to a track. With the new model, artists can select a part of a song and recreate it using prompts without touching other parts of the track.
Additionally, instead of creating short clips, artists can create a song in sections, including the intro, verse, and chorus, and then blend them together. ElevenLabs added that the model performs more reliably in languages, lyrics, vocals and arrangements.
In recent months, AI labs have been racing to release models that can create professional-quality music. Google, Stability AI and Suno new music generation models have also been released with the ability to create larger and more complex tracks. At the Google I/O developer conference, Google added the ability to easily create covers, edit songs by sections, and create music videos using his Flow Music tool.
ElevenLabs emphasized that the new model is based on licensed data and has been cleared for commercial use so that users can use the pieces freely. Surprising offers with tags is key, as other AI music startups like Suno and Audiofaced court cases over copyright issues.
The new model is available in ElevenLabs’ ElevenCreative tool for marketing and branding teams, along with the recently launched ElevenMusic AI-generated song creation platform, with ElevenAPI availability coming soon.
When you purchase through links in our articles, we may earn a small commission. This does not affect our editorial independence.
