Lawrence is a contributing reporter at Engadget, specializing in our AI overlords, musical doodads and, of course, garden variety gaming and tech. To that end, Lawrence once lost badly in multiplayer Mario to Nintendo’s own Shigeru Miyamoto, who laughed gleefully as he threw him down a pit.
, an upgraded version of its music-generation platform. This system lets users create up to three minutes of audio via text prompt. That’s around the length of an actual song, so it'll also whip up an intro, a full chord progression and an outro.
Introducing Stable Audio 2.0 – a new model capable of producing high-quality, full tracks with coherent musical structure up to three minutes long at 44.1 kHz stereo from a single prompt.It primarily works via text prompt, but there’s an option to upload an audio clip. The system will analyze the clip and produce something similar. All uploaded audio must be copyright-free, so this isn’t for the purposes of mimicking something that already exists.
For instance, the system loves adding vocals, but not in any known human language. I guess it’s in whatever language that makes up the text in AI-generated images. The vocals sort of sound like actual people, and other times they sound Gregorian chanters filtered through outer space. It’s right smack dab in the middle of that uncanny valley.
United Kingdom Latest News, United Kingdom Headlines
Similar News:You can also read news stories similar to this one that we have collected from other news sources.
Joey Lawrence Says Brother Matthew Lawrence Is ‘Happy’ Dating ChilliJoey Lawrence weighed in on brother Matthew Lawrence’s relationship with TLC’s Chilli
Read more »
Taylor Swift's 'Eras Tour' Surprise Songs: Which Songs Are Left?Maddie Ellis is a weekend editor at TODAY Digital.
Read more »
Stability AI Launches Stable Audio 2.0 With Audio-to-Audio Generation FeatureStability AI's text-to-music generator Stable Audio got an update that boasts new features including audio-to-audio generation.
Read more »
Stable Audio 2.0: Create AI-Generated Songs with Your Own Audio SamplesStable Audio 2.0 now allows users to upload their own audio samples and create AI-generated songs. The new version offers a full three-minute sound clip, making it suitable for creating complete songs. Unlike OpenAI's Voice Engine, Stable Audio is free and publicly available. The main difference from the previous version is the ability to create songs with an intro, progression, and an outro.
Read more »
The surprising promise and profound perils of AIs that fake empathyMillions of us are turning to chatbots for emotional support. But there are good reasons to think AIs will never be capable of genuine empathy, raising profound questions about their role in society
Read more »
Some Haitian-Americans hopeful resignation of prime minister will lead to stability in troubled homelandThey told CBS New York they hope Ariel Henry stepping down will open the door for a coalition government.
Read more »