Google DeepMind Releases Updated Version of MusicFX DJ: New Breakthrough in AI Music Production Tools

AIbase基地

Published inAI News · 4 min read · Oct 25, 2024

271

Google DeepMind recently launched an updated version of its AI music production tool, MusicFX DJ, designed to serve users with or without professional music knowledge. The company first showcased this software at this year's Google I/O conference.

Unlike conventional DJ software that mixes pre-recorded tracks, MusicFX DJ can generate brand new music in real-time. Users simply input what they want—such as specific genres, instruments, or moods—and the AI will create it instantly.

Google DeepMind stated that the system has undergone two major improvements. Firstly, it can now stream music in real-time by adapting previously offline models. The software creates the next section of music based on what it has already produced and the user's instructions.

Secondly, users can now input multiple prompts at different times, mixing different musical elements, similar to how DJs layer tracks.

MusicFX DJ can produce music in 48kHz stereo studio quality audio, a standard reached by competitor Udio in July with its 1.5 version. Users can export up to 60 seconds of clips and share their sessions with others.

More precise control Google DeepMind stated that the new version of MusicFX DJ provides users with more control over their music. Users can adjust the orchestration, insert musical gaps, and create bass drops at any time. The software also allows you to adjust the speed and musical key while creating.

Meanwhile, Google is testing an AI music feature called "Dream Track" on YouTube. This experiment allows creators in the US to create instrumental tracks simply by inputting what they want. Like all Google's AI-generated content, these music tracks are watermarked with SynthID—the same technology Google recently started using for text.

Currently, these tools are not available to the public. Only selected testers can access the music AI sandbox, and Dream Track is limited to US creators. Google said it will roll out successful features to other products over time.

The music industry has supported this project through Google's "Music AI Incubator". Six-time Grammy winner Jacob Collier helped develop the tool, describing it as "real-time sound putty" that can create surprising connections between unlikely musical elements.

Google DeepMind Predicts AGI May Surpass Humans by 2030 and Releases Safety Strategy

Google DeepMind recently released a comprehensive strategic document outlining its approach to developing safe Artificial General Intelligence (AGI). AGI is defined as a system capable of matching or exceeding human capabilities in most cognitive tasks. DeepMind anticipates that current machine learning approaches, particularly neural networks, will remain the primary path to achieving AGI. The report notes that future AGI systems could potentially surpass human performance and exhibit significant autonomy in planning and decision-making. This technology will have implications for healthcare...

Isomorphic Labs, DeepMind Spin-off, Secures $600 Million to Advance AI Drug Discovery

Isomorphic Labs, a platform focused on AI-powered drug discovery, founded in 2021 as a spin-off from Google's DeepMind, has secured $600 million in Series A funding led by Thrive Capital, with participation from GV and existing investor Alphabet (Google's parent company). This funding will accelerate the further development of Isomorphic's AI drug design engine and support the company's R&D efforts.

Google Releases Open-Source TxGemma Model to Accelerate Therapeutic Drug Discovery

Google recently announced the launch of its new open-source model, TxGemma, designed to significantly improve the efficiency of therapeutic drug development. Developed by the Google DeepMind team, this model is a fine-tuned version of their advanced Gemma model family, incorporating powerful natural language understanding, scientific prediction, and multi-turn dialogue capabilities. TxGemma aims to revolutionize drug discovery. Its release is considered a significant advancement in the application of AI to biomedicine, promising to drastically shorten the time it takes for drugs to move from the lab to clinical trials, while also reducing costs.

Google Unveils Gemini Robotics: AI Model Enabling Human-like Robot Behavior

Google DeepMind has revealed its secret weapon – Gemini Robotics! This is no ordinary roomba; it's about truly infusing AI intelligence into robotic bodies, enabling robots to operate (and potentially even more cleverly) in the physical world, just like humans. The versatile Gemini Robotics is powered by the advanced Gemini 2.0 model. Gemini itself boasts the ability to process text, images, audio, and video.

Google DeepMind Executive: AI Should Enhance Human Abilities, Not Replace Them

At the recent 'Invest Karnataka 2025' conference held in Bangalore, numerous leaders from the technology industry gathered to discuss the transformative potential of artificial intelligence in India and its impacts. Manish Gupta, Senior Director at Google DeepMind, delivered a key speech at the conference, emphasizing the need to establish corresponding regulations alongside technological innovation to ensure responsible development. Note: Image generated by AI, image courtesy service provider Midjourney.

Former DeepMind Scientist Founds Artificial Intelligence Drug Discovery Company

Recently, former DeepMind scientist Simon Kohl announced the establishment of a new artificial intelligence drug discovery company, aiming to leverage his extensive experience in protein prediction, particularly related to the Nobel Prize-winning AlphaFold system. AlphaFold is a revolutionary AI tool that can accurately predict the three-dimensional structure of proteins, a breakthrough that has garnered significant attention in biomedical research. Image source note: Image generated by AI, image licensed service.