ElevenLabs 发布音乐生成模型 Music v2.5

Domain: elevenmusic.io Points: 41 | Comments: 34 [Top Comments] - Gosh, the voice singing “unlimited downloads!” but the underlying text saying “400 per day” sure hit hard. As if generative AI needed more publicity for its “we are literally just making stuff up” approach to getting stuff done. Cool presentation, but who signed off on this? - My favorite was right before that. Text: You have rights to what you make. Music: You own what you make. - > As if generative AI needed more publicity for its “we are literally just making stuff up” approach to getting stuff done. To be fair, there are technical considerations. Like, *technically,* nobody in charge of these companies gives a shit about misleading people. - I don't think this could be a model issue with not following properly (I hope for the sake of ElevenLabs), otherwise this would the most botched model release we've seen so far. Their main product release with a demo and not a single person listened to/read that demo and noticed the difference?! Something must have happened here, miscommunication between departments so the blog post authors/owners and whoever made the actual music generation missed some update in-between when they made this and the release. If it's truly that the model chose not to follow passed lyrics/hallucination, and they still released this, I'd be lost for words. - Great sound quality, definitely better than Suno 5 and 6. It let me download a WAV file which goes unfiltered up to 20kHz (Suno goes to ~15kHz and has more artefacts). Here is my first attempt: And here are some Suno v5 tracks with the same prompt for comparison: All in all, Suno still has much better musicality (or at least had in version 5), but the sound quality of elevenmusic is clearly better. - This probably corresponds to compute. ElevenLabs can burn compute for now, Suno can’t. - highly recommend clicking "Listen to this blog post". Not what I was expecting... - The music shows the post before legal got to put their hands on it lmao.. - It's interesting to see there are text differences between the audio and the blog post. At the point where it vocalizes unlimited downloads by Plus users, the text says 400. I wonder if that's hallucination or a post-music-generation edit. - Completely agree! First time seeing something like this. - Incredibly depressing - Why? I use to work as a dj 15 years ago , this is just a dream ! - The demo is actually pretty good - Note that ElevenLabs claims the right to train on any data you upload to the service, such as editing a song you made etc. > (d) License to Your Content and NILV. You hereby grant to ElevenLabs a license to use, reproduce, modify, adapt, publish, translate, create derivative works from, distribute, make available, communicate to the public, publicly perform, display, and use your Uploaded Music and Input (including your name, image, likeness, voice rights and other indicia of your persona that may be embodied in your Uploaded Music or Input (collectively, “NILV”)) and your Output, in each case, to provide the Services (including the trust and safety features therein), to promote and improve the Services, and to develop and improve our other services and products. Such license shall be… - Are people asking for this to exist? There isn't a big enough pool of talented humans willing to work for low pay, widely available cheap recording gear and free musical educational material, that music needs to be made even cheaper and soullessly? I'm not against some AI uses, I use LLMs myself where it makes sense, *but music is one of the things that we were told AI would free up all our time to do!!* - This is orders of magnitude cheaper and faster than paying for a song to be created from scratch by a human. - > Are people asking for this to exist? There isn't a big enough pool of talented humans willing to work for low pay, that music needs to be made even cheaper and soullessly? Hiring someone is work and takes effort, and can take a few tries. People, especially solo creators, generally don't want to bother, and are excited at what they can now do without requiring people to fill in skills they haven't acquired. This ironically goes for creatives as well! I think it's been telling past week, when Astra demonstrated a step change in 3D modeling/art abilities. I have a few friends who are indie game devs, and who had been excited about AI because it allows them to create without requiring programmers all of a sudden. And they reacted with dismay to Astra - like what many programmers were feeling two years ago. But previously they had not quite been able to empathize and were in no way hiding their enthusiasm about making games without being handicapped by programmer inavailability. This won't replace pop stars; those remain analog because they sell better. This is why South Korea for example went all-in on the idol system of kpop: South Korea had pervasive broadband before most other markets, so when MP3 came along physical album sales crashed over night. Music companies shifted to the most analog product they could think of: People. (I'm almost literally quoting J.Y. Park.) It might well replace the session musician you hire to sing the demo tape that's delivered to those pop stars to model their performance on, though. The moral debate also isn't entirely new to music production, with software emulations having replaced many physical instruments and having put plenty of instrument or gear makers out of work. Counter-example: This is pre-AI, but I also have a friend who runs a very successful small company in a niche he's all but cornered. When he started he needed a programmer, and he found this almost-no-cost kid working from his parents' home in a small village - this is for things like elevator and lobby music, background music for infomercials etc... it's simply not economically plausible to hire a person, plus it's a hassle, and royalty free libraries are a hassle to use. - I chose to listen to the blog post instead of just reading it. I don't know how much if it is just the *idea* of AI-generated music for me, but the listening experience was extremely repulsive. - I hate that this is actually perfectly listenable as background coding music I don't focus on. - What a dream for creation , I already see my daughter in the future will create her own album just for specific event or party . It’s almost like dj but now you’re not just picking tracks of a similar theme , you choose a theme , and the rest of the music bands . Wow . - Hugged to death - If only ... - >ElevenLabs recently announced a multi-year strategic agreement with Universal Music Group (UMG) spanning licensing and product development. This agreement is separate from Music v2.5. I am more interested in knowing what this will bring in the future. This is bigger than their 2.5 or whatever version. - Impressive technology I guess, but god things are trending in such a soulless direction.