Since 2020, there are a number of new models, for example: - Stable Audio: https://stability-ai.github.io/stable-audio-demo/ https://www.stableaudio.com/ - MusicGen: https://ai.honu.io/papers/musicgen/ - MusicLM: https://google-research.github.io/seanet/musiclm/examples/. - Source: Hacker News / about 1 month ago
Yes, there is MusicLM by a Google research team. You could even make transitions between multiple soundalikes, see Story Mode. Source: 10 months ago
Google has the most advanced IMO: Https://google-research.github.io/seanet/musiclm/examples/. Source: 11 months ago
You may have had the ability to generate music like that for over a month now through MusicLM: https://blog.google/technology/ai/musiclm-google-ai-test-kitchen/ https://google-research.github.io/seanet/musiclm/examples/. - Source: Hacker News / 11 months ago
I'm guessing it's MusicLM: https://google-research.github.io/seanet/musiclm/examples/. Source: 12 months ago
The original MusicLM publication had rather long and detailed prompts, some including multiple parts with timed transitions. Source: 12 months ago
Google has a text to music generating AI, they could plug that into Bard (making the name more appropriate) and probably get some more traction in this AI race. Source: 12 months ago
A friend was a full time jazz musician for years (he’s not famous but played with many/most of the big names in jazz) and said it < https://google-research.github.io/seanet/musiclm/examples/> was really interesting to him, musically. Sort of like the ideal for a jazz band, because you’ve got all independent instruments but coming together from a single “mind”. - Source: Hacker News / 12 months ago
Here's some examples if people haven't heard MusicML yet. Source: 12 months ago
Non-clickbait link: https://aitestkitchen.withgoogle.com/experiments/music-lm Its part of AI test kitchen, if you were already part of that for playing with BARD and stuff you just need to log in and give it a go. If not, you'll have to get on the waitlist. When I asked I got access within a day, but might be much slower now with so much interest. Here are a bunch of examples of the music:... - Source: Hacker News / 12 months ago
FYI, this is MusicLM, which was just recently published and appears to be way ahead of anything out there so far. You can check out examples here https://google-research.github.io/seanet/musiclm/examples/ So this is not just empty PR by Google. - Source: Hacker News / 12 months ago
Google has made MusicLM available through a waitlist via their AI Test Kitchen. All you do is give it a prompt and it generates a sample. Source: 12 months ago
For reference last two big steps up in AI music generation are this https://openai.com/research/jukebox which is still pretty grainy, andhttps://google-research.github.io/seanet/musiclm/examples/ which is a HUGE step up but not available yet and definitely wasnt in 2022. Source: 12 months ago
Possible "no-effort" near-term BG music solution but YMMV on the quality: https://google-research.github.io/seanet/musiclm/examples/. Source: about 1 year ago
Google unveils MusicLM, an AI that can generate music 🎵 from text prompts. Check out the initial samples, they are really nice . Source: about 1 year ago
You could very well be right, I have no idea what I am talking about either! What I think might be used as prompt is human trying to imitate that sound. Google used something like this with their MusicLM model. Check out "Text and Melody Conditioning" section, it's crazy. https://google-research.github.io/seanet/musiclm/examples/. Source: about 1 year ago
Not released yet but look at Google’s music lm on this page and Check out the text and melody conditioning. A guy hums and the so turns it into s synth or electric guitar or jazz with a saxophone or a opera singer or string quartet ect. Hopefully it gets released https://google-research.github.io/seanet/musiclm/examples/. Source: about 1 year ago
A.i and music production is here amongst us already! You can already use ChatGPT to generate melodies and chords for you, also worth looking at Googles Music LLM, which is the ability to tell the ai what sort of song you want in words, and it will generate based on your description, you can hear some of the results here as its not public yet: https://google-research.github.io/seanet/musiclm/examples/. Source: about 1 year ago
Google has a text to music AI in development but it isnt available to the public. It's pretty amazing though. Music LM. Source: about 1 year ago
Stuff like this is becoming more common as AI research advances, and TTS models are also improving. Not sure what models the AI music stuff that's imitating artists is using though so can't provide info on that. Source: about 1 year ago
And similar systems for music, transformed or completely generated voices, and 2D and 3D animation will further speed up asset creation and will make less expensive quality assets widely available. Source: about 1 year ago
Do you know an article comparing MusicLM by Google to other products?
Suggest a link to a post with product alternatives.
This is an informative page about MusicLM by Google. You can review and discuss the product here. The primary details have not been verified within the last quarter, and they might be outdated. If you think we are missing something, please use the means on this page to comment or suggest changes. All reviews and comments are highly encouranged and appreciated as they help everyone in the community to make an informed choice. Please always be kind and objective when evaluating a product and sharing your opinion.