Meta Platforms has unveiled Movie Gen, a new family of AI models that generates video and audio content. Coming to Instagram next year, Movie Gen also allows a high degree of editing and effects customization using text prompts. Meta CEO Mark Zuckerberg demonstrated its abilities last week in an example shared on his Instagram account, where he sends a leg press machine at the gym through transformations as a steam punk machine and one made of molten gold. The models have been trained on a combination of licensed and publicly available datasets. Continue reading Meta’s Movie Gen Model is a Powerful Content Creation Tool

New York-based ElevenLabs is going global with its generative AI text-to-speech reader app, which can narrate writings in 32 languages with thousands of voices from which to choose. The audio startup promises “high quality, human-like” AI voices that are “emotionally and contextually aware,” adapting delivery of written cues “to achieve a high emotional range.” ElevenLabs has focused on “creative workflow,” with a voice isolator and audio effects generator tools. Its catalog includes the voices of celebrities Judy Garland, Laurence Olivier, James Dean and Burt Reynolds. Custom models for translation and voiceover work using contemporary actors is a future possibility. Continue reading ElevenLabs Reader App Is Available Globally in 32 Languages

New York-based speech synthesis software startup ElevenLabs has launched its latest AI development — Voice Isolator and an API to go with it. Voice Isolator is designed to extract background noise, leaving clear dialogue for film, podcast, and interview post-production. The Voice Isolator API lets developers integrate the new product into third-party applications. To use the technology, content is uploaded and processed by the Voice Isolator model, resulting in what the company claims is speech comparable in quality to that obtained in a recording studio. The app is described as “free, with some limitations.” Continue reading ElevenLabs Voice Isolator Audio Post Tool Released with API

YouTube has released an eraser tool update that makes it easy to remove copyrighted music from videos without disturbing the remaining audio, like dialogue and sound effects. The Erase Song update uses an AI algorithm to detect and remove the offending material, making it more accurate than what had previously been available, as well as easier. Creators whose material has Content ID claims can now excise the objectionable material without having to manually edit and upload a new video, thereby avoiding potential restrictions on where the video is viewable or whether it can be monetized. Continue reading YouTube AI Song Eraser Easily Removes Copyright Material

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

Stability AI has added another audio product to its lineup, releasing the open-source text-to-audio generator Stable Audio Open 1.0 for sound design. The new model can generate up to 47 seconds of samples and sound effects, including drum beats, instrument riffs, ambient sounds, foley and production elements. It also allows for adapting variations and changing the style of audio samples. Stability AI — best known for the image generator Stable Diffusion — in September released Stable Audio, a commercial product that can generate sophisticated music tracks of up to three minutes. Continue reading Stability AI Releases Free Sound FX Tool, Stable Audio Open

ElevenLabs has launched its text-to-sound generator Sound Effects for all users, available now at the company’s website. The new AI tool can create audio effects, short instrumental tracks, soundscapes and even character voices. Sound Effects “has been designed to help creators — including film and television studios, video game developers, and social media content creators — generate rich and immersive soundscapes quickly, affordably and at scale,” according to the startup, which developed the tool in partnership with Shutterstock, using its library of licensed audio tracks. Continue reading ElevenLabs Launches an AI Tool for Generating Sound Effects

ZTE has launched what it calls the world’s first AI-powered, eyewear-free 5G 3D tablet, the Nubia Pad 3D II. The 12.1-inch LCD display supports 2,560 x 1,600 resolution and 144Hz refresh rate. Powered by a Qualcomm Snapdragon 8 Gen 2 chipset, the Nubia Pad 3D II is equipped with an AI eye-tracking engine that utilizes “high-speed visual sensors and eye-detection algorithms” to enhance response speed and enable accurate synchronization with the users’ eyes in real-time “for a more natural and realistic 3D display experience,” ZTE says. The device also converts 2D to 3D with Neovision 3D Anytime technology. Continue reading ZTE Unveils Glasses-Free Android Tablet, the Nubia Pad 3D II

YouTube’s Creator Music marketplace is officially rolling out to U.S. Partner Program participants starting this week. Creator Music offers a sizable song catalog whose license and use terms are clearly spelled out. Some music is offered on a revenue-sharing basis, allowing creators and rights holders to earn from the end use. In announcing the service in September, YouTube pointed out its creators identified music rights as problematic. Due to the high cost associated with pop tunes, users often opted for unknown music. Creator Music aims to make licensing more recognizable music easy and affordable. Continue reading YouTube Launches Creator Music for Its Partner Participants

More people than ever are using subtitles — often in their native language, to help follow-along with indiscernible audio, according to a study by language-teaching app Preply. Netflix released figures indicating more than 80 percent of its subscribers used subtitles (or closed captions) once a month or more. And the trend is not limited to seniors; younger viewers are about four times more likely to turn on subtitles. The prevalence of rear-facing, or downward-directed speakers in today’s ultra-thin TVs has compounded the problem, often resulting in worse audio than the old-fashioned TV sets, which had front-facing speakers. But there are other issues affecting TV audio. Continue reading Subtitles, Closed Captioning Popular Among Young Viewers

TikTok is debuting new editing tools and one of them, Photo Mode, is drawing comparisons to Meta’s popular Instagram app. “For when you’d prefer to express yourself in formats other than video, we released Photo Mode, a new carousel format available on mobile for photo content that’s ideal for sharing high quality images on TikTok,” the company writes. The launch occurs just as Instagram has begun shifting its emphasis to video, to the consternation of many users, disapproval TikTok may have noticed as it seeks to pick up market share. Continue reading TikTok’s New Toolkit Adds Photo Carousel, Allows More Text

Spotify-owned music-editing software company Soundtrap is launching a new product this week designed to make podcast editing as easy as using Google Docs. Dubbed “Soundtrap for Storytellers,” the web-based production tool allows users to do everything in one place, including recording, editing and mastering audio. As just one example of how easy the product aims to make podcast editing, it will allow users to cut words out of automated transcripts of their recorded conversations and hear the changes reflected in the audio itself.

Continue reading Spotify’s Soundtrap Aims to Simplify Podcast Editing for All

During her keynote at VidCon in Anaheim, YouTube CEO Susan Wojcicki announced new and upcoming tools designed for content creators. Wojcicki unveiled a creator tip jar, analytics app, fan-submitted subtitles, channel management tools and more. The new products are intended to engage a larger worldwide audience, help build successful businesses and manage creative work. She also noted that YouTube’s new ad campaign has helped more than double awareness of creators. Continue reading VidCon 2014: YouTube CEO Unveils New Tools for Creators