ElevenLabs has released Music v2, an upgraded AI music generation model that enables transitions between genres without losing musical coherence. The model can shift between opera and heavy metal, handle fast rap, and embed sound effects while maintaining coherence. According to ElevenLabs, the model was trained only on licensed data, partly through a partnership with music company Believe.
Music v2 powers three platforms: ElevenMusic for musicians, the ElevenAPI for developers, and ElevenCreative for brands and content teams. API pricing is set at $0.15 per minute, with a maximum length of five minutes and audio quality of 44.1 kHz at 128-192 kbps. Users can now regenerate specific sections of a song without affecting the rest through improved inpainting.
Multilingual support has also been upgraded. All generated tracks are cleared for commercial use starting with the Starter+ plan.
Source: thedecoder
