Google DeepMind has unveiled new research on AI tech it calls V2A (“video-to-audio”) that can generate soundtracks for videos. The initiative complements the wave of AI video generators from companies ranging from biggies like OpenAI and Alibaba to startups such as Luma and Runway, all of which require a separate app to add sound. V2A technology “makes synchronized audiovisual generation possible” by combining video pixels with natural language text prompts “to generate rich soundscapes for the on-screen action,” DeepMind writes, explaining that it can “create shots with a dramatic score, realistic sound effects or dialogue.” Continue reading DeepMind’s V2A Generates Music, Sound Effects, Dialogue

Meta Platforms is releasing AudioCraft, a generative AI framework that creates “high-quality,” “realistic” audio and music from text prompts. AudioCraft consists of three models: MusicGen, AudioGen and EnCodec, all of which Meta announced it is open-sourcing. Released in June, MusicGen was trained on Meta-owned and licensed music, and generates music from text prompts, while AudioGen, which was trained on public domain samples, generates sound effects (like honking horns and barking dogs) from text prompts. The EnCodec decoder allows “higher quality music generation with fewer artifacts,” according to Meta. Continue reading Meta’s AudioCraft Turns Words into Music with Generative AI

Apple’s iMovie 3.0 includes new features that make it easier for social users to create edited videos on the iPhone and iPad. Magic Movie will instantly generate videos from user-selected clips and photos, automatically adding transitions, effects and music, while Storyboards offer pre-made templates on which to build. The tools are designed to help “aspiring content creators and moviemakers learn to edit and improve their video storytelling skills,” Apple says, explaining that makers of DIY videos, tutorials, product reviews and the like are the targeted audience. Continue reading iMovie 3.0 Automates Social Video Editing on iPhones, iPads

The BBC introduced “Visual Perceptive Media,” an experimental project out of its R&D unit in Salford, UK, which allows video stories to adapt in response to individuals’ personalities and tastes. The British broadcaster earlier created the audio-based Perceptive Media project; a radio drama makes adaptations based on the listener’s location, time of day and other factors such as proximity to the device and background noise. The video-based project begins with a mobile app that conducts a personalization process. Continue reading The BBC Experiments with TV Shows That Adapt to Personality

YouTube Capture is an easy-to-use app that allows smartphone and tablet owners to record videos of any length that can then be edited and shared. Google updated YouTube Capture for iOS this week with new editing features geared toward those who want to take their creativity beyond simple Vine and Instagram options. With the update, users can easily record video footage, edit, rearrange multiple clips and add music to create a single video. Continue reading YouTube Capture for iOS Update Includes Splicing and Music

For those who purchase the newly released “Man Of Steel: Original Motion Picture Soundtrack” limited deluxe edition CD, a unique feature joins Hans Zimmer’s musical score. The deluxe edition includes an access code to download the Z+ Music app for iOS devices that allows users to play the soundtrack in 11.1 channel surround sound using any headphones, including earbuds. The free Z+ app will soon be available to Android users. Continue reading Music App Plays Man of Steel Soundtrack in Surround Sound