We’ve been cooking up something loud, dark, and beautifully intelligent. Meet Dask Audio — an AI assistant crafted to rescue users from bad playlists and boring audio experiences. Our mission was to turn complex AI algorithms into a warm, immersive, and visually stunning journey. No cold tech vibes here. Instead, we went with glowing neon gradients, futuristic 3D audio shapes, and a dark mode that feels exactly like a premium, late-night concert. 🎸🌌 We had an absolute blast designing this visual universe, pushing the boundaries of how music and AI interact. We hope you feel that raw energy radiating through!

Odyssey just marked two world model firsts back-to-back, dropping Starchild-1, which the company calls the first real-time, multimodal world model, and Agora-1, which lets multiple players interact inside the same AI-generated world. Starchild-1 can generate synchronized audio and video on the fly while taking in and adjusting to user inputs, with no fixed generation length. https://lnkd.in/dxApinuQ

OI - the street kept moving. A short AI video study exploring street-film atmosphere, movement, public space, and emotional drift. The goal was not to create a polished “AI demo,” but to test whether generated footage can hold cinematic continuity: mood, pacing, geography, texture, and a sense of a larger world outside the frame. This sits somewhere between music video development, campaign-world testing, and visual R&D. Open to collaborations around AI video, music visuals, campaign films, and visual identity development. Created as part of my ongoing AI film experiments under kvetcch (https://lnkd.in/drSvDRTN) #AIVideo #CreativeDirection #VisualIdentity #GenerativeAI

It's been a while since I last shared my research here. Over the past few years, I've been unfortunately away from research, but recently I've started getting back into it. Thanks to the opportunity to present at ADC 2026 Japan, I've been updating some of my ideas around Music AI and creative tools. ( https://sched.co/2KCey ) The release of Stable Audio 3 has also inspired me to experiment with new ways of interacting with music generation models. Rather than focusing solely on generating music from prompts, I'm interested in how we can directly interact with and shape generative models as creative tools. Lately, I've been exploring node-based interfaces for navigating embedding and latent spaces. This experimental demo explores how users can define their own semantic dimensions (e.g., dog 🐶 ↔ cat 🐱) from examples and use them to interactively navigate, manipulate, and morph sounds. It's still an early prototype, but I'm excited to share some recent experiments. I'm also preparing an audio plugin based on these ideas, which I'll be sharing soon!! #ADC #audiodevcon

🔥BEYOND HYPERDRIVE: AVA Studios Rewrites the Rules of Digital Realism🔥 What happens when you fuse the raw, unadulterated power of a twin-turbocharged drag monster with cutting-edge, real-time AI rendering? You get the latest visual masterpiece from AVA Studios—a high-octane assault on the senses that pushes past the boundaries of virtual creation. This isn’t just a music video. It’s a declaration of tech-driven disruption. From the first frame, AVA Studios pulls back the curtain on the future. We're talking real-time neural reconstruction, path tracing, and subsurface scattering running flawlessly under the watchful eye of our Content Director. Real Muscle meets Neural Tech The track screams as a custom, flame-spitting Lamborghini drag car tears down the pavement, hitting speeds over 280 km/h with a staggering +55.8gZ of simulated force. It’s a masterclass in combining high-speed physical adrenaline with state-of-the-art digital aesthetics. "We don't need the hype to make it feel real." AVA Studios is proving that when your data is flawless and your rendering is seamless, the work speaks for itself. Watch the full experience now and see where real life ends and next-gen rendering begins. #AVAStudios #NeuralRendering #PathTracing #DigitalRealism #NextGenTech #MusicVideoProduction #CreativeDisruption

How do you make a camera feel alive in just 10 seconds? For this AI-generated Sony A7 III commercial, the goal wasn't simply to showcase a product—it was to visualize the engineering behind it. The concept follows a continuous cinematic camera move around the Sony A7 III, transitioning from macro product details into a fully exploded view of its internal components before seamlessly reassembling into the final hero shot. What fascinated me most was how AI can now be used not only for storytelling, but also for creating high-end product visualization experiences that previously required extensive 3D production pipelines. Curious to see where AI-powered commercial production goes next. Sony #AI #GenerativeAI #AIVideo #CreativeAI #Sony #SonyA7III #ProductVisualization #CommercialProduction #MotionDesign #Filmmaking #Advertising #CreativeDirection #VisualEffects #3DAnimation #BrandMarketing #ContentCreation #DigitalCreativity #TechAdvertising #ProductDesign #Innovation

Europe. AI. Audio. These three spaces have been core passions of mine for a long time. That’s why I’m very excited to share what we’ve been cooking up at Mirelo.ai over the past few months. As a European frontier AI research lab focused purely on Audio, our mission is simple: give creators, sound mixers, and video editors access to great audio faster. Our foundational models generate and perfectly sync sounds based on video or text prompts, eliminating the tedious bottlenecks of audio post-production. Today, we're taking a massive step forward with the launch of Mirelo SFX 1.6. This new model brings next-generation AI audio capabilities directly into your workflow via our API, plugins, and Studio: - Extend a sound to perfectly fit your scene. - Create seamless loops for beds and atmospheres. - Fix audio glitches without starting from scratch. A huge congrats to the whole Mirelo team for shipping this new model along with a new website, a new Studio, 3 new AI tools and a new brand. Intrigued? You can put the model to the test right now. 👉 Give it a spin for free at www.mirelo.ai

New Post: An AI‑Driven Adaptive Lighting Control System for Live Electronic Music Performances Using Sensor Fusion and Reinforcement Learning - ## Abstract The convergence of artistic practice and emerging technologies creates new possibilities for immersive, responsive experiences. This exploratory scaffold proposes a synthetic, simulated, and projected framework that integrates real‑time audio, performer motion, and environmental sensing with a deterministic‑policy reinforcement‑learning \(RL\) controller to drive lighting cues during live electronic‑music performances. Synthetic evaluation across five 30‑minute \[…\] \[Source & Legal Disclaimer\] This is an AI-generated simulation research dataset provided by Freederia.com, released under the Apache 2.0 License. Users may freely modify and commercially use this data \(including patenting novel improvements\); however, obtaining exclusive patent rights on the original raw data itself is prohibited. As this is AI-simulated data, users are strictly responsible for independently verifying existing copyrights and patents before use. The provider assumes no legal liability. For future Enterprise API access and bulk dataset purchase inquiries, please contact Freederia.com.

Headline: 30 Years of Sound, and the New Frontier of AI. Thirty years ago, when we founded Live Tone, the landscape of cinema sound was a different world. From the tactile warmth of analog tapes to the immersive precision of Dolby Atmos, I have spent three decades sculpting the auditory heartbeats of over 400 films. Today, as I celebrate this 30-year milestone, I find myself standing at another monumental crossroads: The Age of AI. Many ask if AI will replace the "ear" of a sound designer. My 30 years in the mixing bay tell me otherwise. Technology has always been the vessel, but the narrative is the soul. At Live Tone, we aren’t just observing the AI revolution; we are integrating it. We are exploring how generative AI can handle the technical labor—the noise, the matching, the restoration—so that we, as artists, can focus on the 'Intent of Sound.' AI can replicate a frequency, but it cannot yet replicate the "silence" that makes a viewer hold their breath in a Bong Joon-ho scene. As I look forward to the next 30 years, my mission remains unchanged: to use every tool at our disposal—from the vintage console to the most advanced neural networks—to ensure that sound remains the most powerful, invisible storyteller in cinema. Thank you to every director, producer, and engineer who has been part of this journey. The best is yet to be heard. #LiveTone30 #SoundDesign #CinemaSound #AIinFilm #PostProduction #AcademyMember #RalphChoi #KMovie #Parasite #Innovation

This FREE Toolkit for Unreal Engine generates procedural soundscapes, ambiences and vehicles in seconds! The past year I've been developing a toolkit for Granular Synthesis inside Unreal Engine. Well, the development has concluded and the toolkit is now available for FREE on Fab! Thanks again to everyone who contributed their feedback and suggestions, I couldn't have done it without you. I hope this toolkit inspires you to get creative with procedural audio. Happy sound designing! 😁 Fab listing: https://lnkd.in/eY-59vUa Showcase video: https://lnkd.in/ebKFzDpm