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

Stability Audio 3.0 small model can run on-device and generate two-minute long tracks ...
CNET

6 Months of AI Radio Went About as Badly as You'd Expect

The experiment was simple. A company gave four AI models $20 each and a fistful of instructions, then left them to their own ...

Visualizing sound: Scientists reveal hidden behaviors of sound waves

An international team of scientists has developed a new analysis of how sound waves behave, revealing surprising effects that ...
Mongabay News

From caws to code: AI helps decrypt animal communication

What are carrion crows saying to each other? Answering that question has been Vittorio Baglione and Daniela Canestrari’s ...

Corti's new Symphony for Speech-to-Text model beats OpenAI at medical terminology accuracy, highlighting the value of specialized AI

Credit: VentureBeat made with OpenAI ChatGPT-Images-2.0 Today, Copenhagen-based healthcare AI Corti is launching Symphony for ...

OpenAI Bought Company That Offered A.I. Tools for Cloning Voices

The acquisition, Weights.gg, was a sort of social network for creating and sharing artificial intelligence algorithms.
GitHub

An Agentic System for Scalable Articulated 3D Asset Generation.

Articraft transforms the creation of articulated 3D assets into a programmatic, code-generation workflow powered by LLMs. Engineered for large-scale dataset generation, it bypasses heavyweight manual ...