← Back to Model Beat
Models·Jul 23·all news from July 23, 2026

Flux 3 generates videos with native audio up to 20 seconds long, a first for Black Forest Labs

Black Forest Labs has released Flux 3, a multimodal foundation model capable of generating up to 20 seconds of video with integrated, native audio. This update marks a technical milestone for the company, as it is their first model designed to process images, video, and audio simultaneously. By enabling synchronized sound generation directly within the video creation process, the tool aims to compete with existing generative video platforms like Seedance 2.0.

Covered by 1 source

Related stories

ModelsOne tampered ChatGPT link could spawn a rogue AI agent that took orders from an attacker every five minutesJul 22 · 34 sourcesModelsChina’s Moonshot to Release Breakthrough AI Model for DownloadJul 25 · 58 sourcesModelsIntroducing Claude Opus 5Jul 24 · 15 sourcesModelsMicrosoft and Mistral strike multi-billion-dollar deal to build AI infrastructure across EuropeJul 21 · 97 sources