Stable Audio Open Released by Stability AI as an Open-Source Text-to-Audio Generator

Stability AI has released an open-source artificial intelligence (AI) model dubbed Stable Audio Open. Users can leverage the model to generate up to 47 seconds of samples and sound effects. Users can use it to create samples of musical instruments or ambient sounds. The AI model also allows users to generate different variations and styles of a previously generated sample. The open-source model is separate from the AI firm’s Stable Audio platform which allows users to generate up to three-minute-long tracks and is only available as part of a subscription.

Stability AI Releases Stable Audio Open

Stable Audio Open works similarly to many available AI models in the market. Users can write a text prompt for a sample or sound effect and it will generate up to 47 seconds of audio. Stability AI mentioned in a newsroom post that the AI model was released in open source to empower sound designers, musicians, and creative communities.

However, it has limited the use of Stable Audio Open to research and non-commercial usage. To get commercial rights, users will have to purchase a Stability AI membership.

In terms of features, it can generate drum beats, instrument riffs, ambient sounds, foley recordings and other audio samples. Further, users can also fine-tune the model using their custom audio data.

Highlighting an example, the AI firm says a drummer can train the AI on recordings of their drumming sessions and use the model to generate new beats. While the model can generate short audio samples, it is not optimised for full songs, melodies, or vocals.

To train Stable Audio Open, the company used a dataset of 4,86,492 audio recordings sourced from FreeSound and Free Music Archive. It added, “We conducted an in-depth analysis to ensure no unauthorised copyrighted music was present in our training data before we began training.”

However, Stability AI also said that the dataset lacks diversity and all cultures were not equally represented. As a result, the generated samples will reflect biases from the training data. To access the AI model, users can go to the company’s Hugging Face listing, where the open model weights are currently hosted.

For the latest tech news and reviews, follow Gadgets 360 on X, Facebook, WhatsApp, Threads and Google News. For the latest videos on gadgets and tech, subscribe to our YouTube channel. If you want to know everything about top influencers, follow our in-house Who’sThat360 on Instagram and YouTube.


WhatsApp Reportedly Begins Beta Testing New Layout for Status Updates With Preview Feature



Check out our Latest News and Follow us at Facebook

Original Source

Getty Images Sues Stability AI; Accuses Stealing, Misuse of Images to Train AI System

Stock photo provider Getty Images has sued artificial intelligence company Stability AI, accusing it in a lawsuit made public on Monday of misusing more than 12 million Getty photos to train its Stable Diffusion AI image-generation system.

The lawsuit, filed in Delaware federal court, follows a separate Getty case against Stability in the United Kingdom and a related class-action complaint filed by artists in California against Stability and other companies in the fast-growing field of generative AI.

Getty declined to comment on the Delaware lawsuit. Representatives for Stability did not immediately respond to a request for comment Monday. Reuters News competes with Getty in the market for images for editorial use.

London-based Stability AI released Stable Diffusion, an AI-based system for generating images from text inputs, and image generator DreamStudio last August. The company announced in October that it had raised over $100 million (nearly Rs. 830 crore) in funding, and has been valued at $1 billion (nearly Rs. 8,280 crore).

Seattle-based Getty accused Stability of copying millions of its photos without a license and using them to train Stable Diffusion to generate more accurate depictions based on user prompts.

Getty said its pictures are particularly valuable for AI training because of their image quality, variety of subject matter and detailed metadata.

Getty said it has licensed “millions of suitable digital assets” to other “leading technology innovators” for AI-related purposes, and that Stability infringes its copyrights and competes with it unfairly.

The lawsuit also accuses Stability of infringing Getty’s trademarks, citing images generated by its AI system with Getty’s watermark that Getty says could cause consumer confusion.

Getty asked the court to order Stability to stop using its pictures and requested money damages that include Stability’s profits from the alleged infringement.

© Thomson Reuters 2023
 

 


Affiliate links may be automatically generated – see our ethics statement for details.

Check out our Latest News and Follow us at Facebook

Original Source

Exit mobile version