Create text to audio tracks: Stability AI introduces tool for music enthusiasts; check here for its availability and pricing

Stability AI, renowned for its groundbreaking AI-generated visuals, has unveiled a groundbreaking text-to-audio generative AI platform named ‘Stable Audio’ to create personalised audio tracks. This innovative platform harnesses the power of a diffusion model, the same technology that fuels Stability AI's popular image platform, ‘Stable Diffusion.’

However, with Stable Audio, the focus shifts from images to audio, allowing users to effortlessly create songs or background audio for various projects.

Today we're thrilled to launch Stable Audio, our first AI product for music and sound generation!

Try it out here for free! #stabilityAI #stableaudio #newannouncement
https://t.co/pRK3Qs9Fak pic.twitter.com/cZfbK1mZYA

— Stability AI (@StabilityAI) September 13, 2023

Get your customisable audio lengths

Traditional audio diffusion models often produce fixed-length audio clips, which isn't ideal for music production, where song lengths can vary significantly.

Stable Audio breaks free from this limitation by enabling users to generate sounds of different durations. Achieving this required a unique approach—Stability AI trained the model on music while incorporating text metadata to mark the start and end times of songs.

"Stable Audio represents cutting-edge audio generation research by Stability AI’s generative audio research lab, Harmonai. We continue to improve our model architectures, datasets, and training procedures to improve output quality, controllability, inference speed, and output length."

Stability AI

Pricing & usage Stable

Audio offers three pricing tiers to cater to different needs:

- A free version that permits users to create up to 45 seconds of audio for 20 tracks each month.

- A professional level priced at $11.99, allowing for 500 tracks of up to 90 seconds each.

- An enterprise subscription, offering customisable usage and pricing for companies.

It's important to note that users of the free version cannot use audio created with Stable Audio for commercial purposes.

A growing trend in AI sound generation

While Stable Audio represents a significant leap in AI sound generation, it's not the only player in the field. Other major names in generative AI, such as Meta and Google, have also ventured into text-to-audio generation, primarily for researchers and audio professionals. These platforms aim to expedite workflows, particularly when creating background music for podcasts and videos.

Stability AI's foray into audio generation, alongside their ongoing expansion into video and 3D images, underscores the rapid evolution of AI technology in reshaping creative industries.