Stability AI, famous for its AI-powered image generators like Stable Diffusion and Stable Doodle, has ventured into the world of music with its latest creation, Stable Audio.

Stable Audio, powered by a diffusion model akin to its image-focused counterparts, can craft audio clips based on textual descriptions. Users provide keywords, specify a desired duration, and await the result.

What sets Stable Audio apart is its adaptability in generating music of varying lengths, thanks to an innovative model trained on music, supported by text metadata indicating the start and end times.

The dataset behind Stable Audio comprises over 800,000 audio files, including music, sound effects, and instrument stems, offering users a wide canvas for musical creativity. It's worth noting that the generated audio cannot be used for commercial purposes without a subscription.

While Stable Audio is primarily targeted at content creators rather than professional musicians, its potential applications are vast, from crafting background music for podcasts and videos to creating unique soundscapes.

Runway Unveils a New AI Model for Generating Videos
Runway, a startup known for co-creating the popular text-to-image AI model Stable Diffusion, has recently unveiled a new artificial intelligence model capable of generating short videos based on text prompts.

The tool is available in three models: a free version offering up to 20 compositions lasting 45 seconds each per month, a $11.99 monthly Professional subscription that allows users to create 500 tracks up to 90 seconds long, and an Enterprise option for businesses to tailor usage and pricing.