Meta has released another open-source AI model trained on hundreds of thousands of music tracks online.
AI has managed to intrude on most artistic endeavors, and now it’s fully come for the music industry. Meta has now announced the release of the open source version of its music generation AI model that uses simple prompts to generate music like ChatGPT or other large language model-based AI generate text.
… [T]he model uses an EnCodec audio tokenizer based on a transformer language model. Users can demo MusicGen through Hugging Face’s API, though, generating some music could take some time depending on how many users are using it at once. You can use the Hugging Face site to create your own instance of the model for much faster outputs. Otherwise, you can download the code and run it yourself if you have the know-how and the rig to support it. — Read More
Tag Archives: Audio
The Rise and Rise of Voice AI
I was wondering about the relative frequency of certain topics that intrigue me in regard to contemporary, technology-oriented sound studies. For a quick glimpse, first I charted “machine listening” in Google Trends, then adding “audio surveillance” and, for a broader swath, “audio deepfake.” The three terms were almost identical in the narrow band of popularity they populated for the past few years. I sought to expand the subject matter with a fourth item, something related to artificial intelligence.
Needless to say, we’re in the midst of AI Summer. These days “AI + [anything]” — following the rise in chatter around DALL-E 2, Midjourney, Stable Diffusion, ChatGPT, DeepMind, Bard, and OpenAI, among other projects — is going to be more popular now than it was even six or seven months ago. — Read More
Apple’s new ‘Personal Voice’ feature can create a voice that sounds like you or a loved one in just 15 minutes
As part of its preview of iOS 17 accessibility updates coming this year, Apple has announced a pair of new features called Live Speech and Personal Voice. Live Speech allows users to type what they want to say and have it be spoken out.
Personal Voice, on the other hand, is a way for people who are at risk of losing their ability to speak to create and save a voice that sounds like them. Apple says it’s designed for people at risk of losing their ability to speak, such as those with a recent diagnosis of ALS. Read More
Google makes its text-to-music AI public
Google today released MusicLM, a new experimental AI tool that can turn text descriptions into music. Available in the AI Test Kitchen app on the web, Android or iOS, MusicLM lets users type in a prompt like “soulful jazz for a dinner party” or “create an industrial techno sound that is hypnotic” and have the tool create several versions of the song. Read More
Paper
Futuri Launches RadioGPT™, The World’s First AI-Driven Localized Radio Content
Live, local, and powered by AI, RadioGPT™ marries GPT-3 technology with Futuri’s TopicPulse content discovery AI and voices generated by artificial intelligence to create the world’s first 100% AI-driven radio hosts.
Cleveland, Ohio, February 23, 2023 — Futuri is revolutionizing the audio industry with the launch of RadioGPT™ — the world’s first AI-driven localized radio content solution. RadioGPT™ combines the power of GPT-3 technology with Futuri’s AI-driven targeted story discovery and social content system, TopicPulse, as well as AI voice tech to provide an unmatched localized radio experience for any market, any format
RadioGPT™ uses TopicPulse technology, which scans Facebook, Twitter, Instagram, and 250k+ other sources of news and information, to identify which topics are trending in a local market. Then, using GPT-3 technology, RadioGPT™ creates a script for on-air use, and AI voices turn that script into compelling audio. Read More
New AI Music
Even more AI songs! Check ’em Out!.
#audioYou Are Grimes Now: Inside Music’s Weird AI Future
Grimes is allowing anyone and everyone to use AI models of her voice — and she’ll split royalties with you, 50/50. Her manager, Daouda Leonard, tells us why they think they’ve found the future of music
WHEN THE ANONYMOUS songwriter/producer Ghostwriter recently dropped “Heart on My Sleeve,” a song built around the AI-cloned voices of Drake and The Weeknd, Universal Music Group moved instantly to remove it from streaming services. But one artist has reacted very differently to the emerging technology. Grimes, whose last album was 2020’s Miss Anthropocene, announced via Twitter on April 23 that anyone can use AI models of her voice “without penalty,” and that she’d split royalties 50/50 with the creator of any successful song doing so. It wasn’t an idle offer; this weekend, she put up an online platform at elf.tech that allows users to post Grimes-infused songs on Spotify and other streaming services under the name GrimesAI-1. Read More
Artificial Intelligence Radio
AI Music
It’s Napster redux.
Universal telling DSPs not to host AI music… What could be better! Think about it, you’re an act that’s so popular, so desirable, that the audience wants even more of your music!
Can we stop trying to hold back the future? It has never ever worked, why should it now? Furthermore, we’ve seen this movie already. What looks scary at first ends up adding to as opposed to taking away. — Read More
AI-Generated Music Is About to Flood Streaming Platforms
There are already countless songs on Spotify, Apple Music, and SoundCloud. And as tunes become easier to create, anyone can add to the copyright din.
IT STARTS WITH a familiar intro, unmistakably the Weeknd’s 2017 hit “Die for You.” But as the first verse of the song begins, a different vocalist is heard: Michael Jackson. Or, at least, a machine simulation of the late pop star’s voice.
It’s just one example of how artificial intelligence is seeping into the music industry. Surf YouTube or TikTok and you’ll find many convincing AI-made covers. The software covers.ai has a waiting list for new users. But there are also tools that can generate instrumentals from text, give people a starting beat or inspiration, and help them to edit tunes. Read More
Rick's Cafe AI 