Stability AI releases a new vocal model that can create six-minute songs

Stability AI, the company behind Stable Diffusion, is launching a new family of audio models, called Stability Audio 3.0. The company claimed that the top model could produce professional-grade music longer than six minutes long.

The company is launching four new models under the Stable Audio 3.0 name: SFX Small (459M parameters), Small (459M parameters), Medium (1.4B parameters), and Large (2.7B parameters). The compact duo is suitable for generating sound and music on the device for up to 2 minutes.

Both the medium and large models can create entire 6-minute and 20-second pieces of music that can maintain the musical structure and melodic tone. That’s more than twice as long as what Stable Audio 2.0, released in 2024, was capable of generating.

Stability AI makes small, small and medium SFX models available with open weights for anyone to use and modify. In 2024, the company released Stable Audio Open, which allowed generating music up to 47 seconds long. The new model family is a big step forward compared to previous open versions.

The big model is only available through API and paid self-hosted services. Additionally, businesses with revenues exceeding $1 million will need to obtain an enterprise license.

Several companies, including Google and ElevenLabs, are releasing templates and tools around music generation. However, as the ongoing legal battles between Sono and Audio have proven, data licensing and partnerships with music companies could become a key part of these services’ long-term survival.

Last year, Stability AI signed deals with Warner Music Group and Universal Music Group to develop models and music creation tools. The company said its latest set of audio models are built on fully licensed data.

The AI ​​startup is developing a new set of products for professional musicians, but did not provide further details about their features. Ethan Kaplan, former digital director at Universal Audio and Fender, joins the company to lead Stability’s professional music offerings.

A number of AI companies are trying to bolster their credentials by hiring music executives. Earlier this year, Suno appointed former Merlin CEO Jeremy Sirota as chief commercial officer. ElevenLabs has also appointed Derek Cournoyer from independent music publisher Kobalt as strategic leader of its music business.