Trending

    Stability AI launches Stability Audio 3.0 with advanced music generation capabilities

    By A47 News Editorial Team·Moderate3 articles covering this·3 news sources·Updated 4 hours ago·World
    Share:
    Stability AI's new audio models for music generation

    Here's what it means for you.

    This innovative technology could redefine music production and creativity.

    What happened

    Stability AI released Stability Audio 3.0, which includes models that can create six-minute songs.

    The Context

    • Licensed Data: The models were trained on licensed data to ensure compliance and quality.
    • On-Device Capability: The small model can run on-device and generate two-minute tracks.
    • Previous Success: This release follows the company's previous success with Stable Diffusion.

    Takeaway

    The introduction of Stability Audio 3.0 may enhance creative possibilities for musicians and content creators.

    3 Articles
    Techmeme

    Stability AI releases a new family of audio models called Stability Audio 3.0 that is trained on licensed data; the top model can generate six-minute songs (Ivan Mehta/TechCrunch)

    Stability AI has launched a new family of audio models named Stability Audio 3.0, which is trained on licensed data and capable of generating music tracks up to six minutes long. This release marks a significant advancement in the company's audio gen...

    TechCrunch

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

    Stability AI has unveiled its latest audio model, Stability Audio 3.0, which is capable of generating music tracks up to six minutes long, marking a significant advancement in AI-generated music technology. The model can also run on-device and produc...

    THE DECODER

    Stability AI launches Stable Audio 3.0 with up to six-minute tracks and open weights

    Stability AI has launched Stable Audio 3.0, a new generation of audio models capable of generating music tracks up to six minutes long, with three models shipping with open weights and trained entirely on licensed data.