My takeaway: Audio is finally becoming interactive.
You don’t mix sound anymore, you point at intent. That’s what Meta’s SAM Audio project is pointing toward, and it has real implications for creators, product teams, and anyone building with multimodal AI. Watch the full video
CREATIVE AI
-
Meta SAM Audio Makes Interactive Sound Design Intent-Based
By
–
-
AI Model Splits Audio Into Target Sound and Background
By
–
Under the hood, the model does one powerful thing: It splits sound into two parts → → The target sound
→ Everything else That single capability unlocks a lot → → Faster editing for creators
→ Cleaner, more controllable data for AI training
→ Multimodal systems that -
AI Audio Tool Adapts to Human Intent Through Multiple Interfaces
By
–
The big unlock is simple but profound: Instead of forcing humans to adapt to audio tools, the model adapts to human intent. You can guide it three ways → → Type what you want, like “keep only the voice”
→ Click where the sound happens in the video
→ Mark a moment in time -
Meta’s AI Audio Editing Tool Simplifies Sound Cleaning
By
–
What if cleaning audio was as easy as clicking on a pixel?
— Ronald van Loon (@Ronald_vanLoon) 20 avril 2026
Not tweaking EQs.
Not guessing with filters.
Just pointing to the sound you want, and telling the AI, keep this.
I’ve been digging into @Meta’s latest work, and it quietly changes how we think about audio editing. pic.twitter.com/xag6nbEavdWhat if cleaning audio was as easy as clicking on a pixel? Not tweaking EQs.
Not guessing with filters. Just pointing to the sound you want, and telling the AI, keep this. I’ve been digging into @Meta
’s latest work, and it quietly changes how we think about audio editing. -
Image Models Generate Surreal Yet Realistic Outputs
By
–
I wish image models could make outputs like this. Absurdity level realism.
-
Claude Cowork and GPT-Image-2: Automation Tools for Everyone
By
–
Tools for the Rest of Us Claude Cowork: Now GA for macOS/Windows. It brings file and task automation to non-developers through a simple desktop interface. GPT-image-2: OpenAI’s next-gen generator is viral for its incredible text accuracy and structural editing capabilities.
-
Humanoid robots compete in creativity despite speed limitations
By
–
Robots can lose the race – but not the creativity! https://
youtu.be/5wcZDZKQ77c?si
=wBEePxyGv7_sTe6i
… via @YouTube #humanoidtech #humanoid #robot #Robotics #AI #TechRevolution #TechInnovation #ArtificialInteligence #PhysicalAI @AlbertoEMachado @Eli_Krumova @postoff25 @Khulood_Almani @anand_narang -
Markerless AI Tracking Transforms Fencing Into Real-Time 4D Geometry
By
–
Markerless tracking on every sword tip overlaid on live footage in real time. Fencing becomes a 4d geometry problem where both players are solving for the same point in space & time. Watching 3d trajectories render live like this is doing something to my brain I cannot explain. https://t.co/FPF18gqDMU
— Bilawal Sidhu (@bilawalsidhu) 20 avril 2026Markerless tracking on every sword tip overlaid on live footage in real time. Fencing becomes a 4d geometry problem where both players are solving for the same point in space & time. Watching 3d trajectories render live like this is doing something to my brain I cannot explain.
-
Imagining Atlantis: NBP to Stable Diffusion 2 Image Generation
By
–
Imagining Atlantis (NBP to SD2) pic.twitter.com/ocGheJNfna
— fofr (@fofrAI) 19 avril 2026Imagining Atlantis (NBP to SD2)
