TE
TechEcho
Home24h TopNewestBestAskShowJobs
GitHubTwitter
Home

TechEcho

A tech news platform built with Next.js, providing global tech news and discussions.

GitHubTwitter

Home

HomeNewestBestAskShowJobs

Resources

HackerNews APIOriginal HackerNewsNext.js

© 2025 TechEcho. All rights reserved.

Show HN: Sonauto API – Generative music for developers

127 pointsby zaptrem3 months ago
Hello again HN,<p>Since our launch ten months ago, my cofounder and I have continued to improve our music model significantly. You can listen to some cool Staff Picks songs from the latest version here <a href="https:&#x2F;&#x2F;sonauto.ai&#x2F;">https:&#x2F;&#x2F;sonauto.ai&#x2F;</a> , listen to an acapella song I made for my housemate here <a href="https:&#x2F;&#x2F;sonauto.ai&#x2F;song&#x2F;8a20210c-563e-491b-bb11-f8c6db92ee9b">https:&#x2F;&#x2F;sonauto.ai&#x2F;song&#x2F;8a20210c-563e-491b-bb11-f8c6db92ee9b</a> , or try the free and unlimited generations yourself.<p>However, given there are only two of us right now competing in the &quot;best model and average user UI&quot; race we haven&#x27;t had the time to build some of the really neat ideas our users and pro musicians have been dreaming up (e..g, DAW plugins, live performance transition generators, etc). The hacker musician community has a rich history of taking new tech and doing really cool and unexpected stuff with it, too.<p>As such, we&#x27;re opening up an API that gives full access to the features of our underlying diffusion model (e.g., generation, inpainting, extensions, transition generation, inverse sampling). Here are some things our early test users are already doing with it:<p>- A cool singing-to-video model by our friends at Lemon Slice: <a href="https:&#x2F;&#x2F;x.com&#x2F;LemonSliceAI&#x2F;status&#x2F;1894084856889430147" rel="nofollow">https:&#x2F;&#x2F;x.com&#x2F;LemonSliceAI&#x2F;status&#x2F;1894084856889430147</a> (try it yourself here <a href="https:&#x2F;&#x2F;lemonslice.com&#x2F;studio">https:&#x2F;&#x2F;lemonslice.com&#x2F;studio</a>)<p>- Open source wrapper written by one of our musician users: <a href="https:&#x2F;&#x2F;github.com&#x2F;OlaFosheimGrostad&#x2F;networkmusic">https:&#x2F;&#x2F;github.com&#x2F;OlaFosheimGrostad&#x2F;networkmusic</a><p>- You can also play with all the API features via our consumer UI here: <a href="https:&#x2F;&#x2F;sonauto.ai&#x2F;create">https:&#x2F;&#x2F;sonauto.ai&#x2F;create</a><p>We also have some examples written in Python here: <a href="https:&#x2F;&#x2F;github.com&#x2F;Sonauto&#x2F;sonauto-api-examples">https:&#x2F;&#x2F;github.com&#x2F;Sonauto&#x2F;sonauto-api-examples</a><p>- Generate a rock song: <a href="https:&#x2F;&#x2F;github.com&#x2F;Sonauto&#x2F;sonauto-api-examples&#x2F;blob&#x2F;main&#x2F;rock_song_generator.py">https:&#x2F;&#x2F;github.com&#x2F;Sonauto&#x2F;sonauto-api-examples&#x2F;blob&#x2F;main&#x2F;ro...</a><p>- Download two songs from YouTube (e.g., Smash Mouth to Rick Astley) and generate a transition between them: <a href="https:&#x2F;&#x2F;github.com&#x2F;Sonauto&#x2F;sonauto-api-examples&#x2F;blob&#x2F;main&#x2F;transition_generator.py">https:&#x2F;&#x2F;github.com&#x2F;Sonauto&#x2F;sonauto-api-examples&#x2F;blob&#x2F;main&#x2F;tr...</a><p>- Generate a singing telegram video (powered by ours and also Lemon Slice&#x27;s API): <a href="https:&#x2F;&#x2F;github.com&#x2F;Sonauto&#x2F;sonauto-api-examples&#x2F;blob&#x2F;main&#x2F;singing_telegram.py">https:&#x2F;&#x2F;github.com&#x2F;Sonauto&#x2F;sonauto-api-examples&#x2F;blob&#x2F;main&#x2F;si...</a><p>You can check out the full docs&#x2F;get your key here: <a href="https:&#x2F;&#x2F;sonauto.ai&#x2F;developers">https:&#x2F;&#x2F;sonauto.ai&#x2F;developers</a><p>We&#x27;d love to hear what you think, and are open to answering any tech questions about our model too! It&#x27;s still a latent diffusion model, but much larger and with a much better GAN decoder.

29 comments

webprofusion2 months ago
Interesting that Suno et al miss out on the obvious problem that actual musicians need extra musicians for their own projects.<p>For instance a guitarist will have a track they wish they had vocals for(and lyrics) for and if they could pay for that they would.<p>Literally if you could highlight a tune section in your DAW, prompt it, and vocals + lyrics were generated, possibly different version or harmonies for existing parts etc. Musicians already pay for plugins but the singing ones are awful to use so far.
评论 #43252277 未加载
评论 #43255540 未加载
mco3 months ago
On one hand this is impressive, and I&#x27;ve been wondering when something like this would appear. On the other hand, I am -- like others here have expressed -- saddened by the impact this has on real musicians. Music is human, music theory is deeply mathematical and fascinating -- &quot;solving&quot; it with a big hammer like generative AI is rather unsatisfying.<p>The other very real aspect here is &quot;training data&quot; has to come from somewhere, and the copyright implications of this are beyond solved.<p>In the past I worked on real algorithmic music composition: algorithmic sequencer, paired with hardware- or soft- synthesizers. I could give it feedback and it&#x27;d evolve the composition, all without training data. It was computationally cheap, didn&#x27;t infringe anyone&#x27;s copyright, and a human still had very real creative influence (which instruments, scale, tempo, etc.). Message me if anyone&#x27;s still interested in &quot;dumb&quot; AI like that. :-)<p>Computer-assisted music is nothing new, but taking away the creativity completely is turning music into noise -- noise that sounds like music.
评论 #43252175 未加载
评论 #43250880 未加载
评论 #43257754 未加载
评论 #43252377 未加载
评论 #43250558 未加载
akrymski2 months ago
I really wish this trend of prompting gen AI models with text would stop. It&#x27;s really meaningless. Musicians need gen AI they can prompt with a melody on their keyboard. Or a bit of whistling into the microphone. Or a beat they can tap on the table. That is what allows humans to unleash their creativity. Not AI generating random bits that fit a distribution of training data. English language is not the right input for anything except for information retrieval tasks.
评论 #43259650 未加载
评论 #43251647 未加载
评论 #43252482 未加载
8474_s2 months ago
The current AI music apps have a certain chunking problem: they force extending the song with segments that may or may not fit, which users likely choose as &quot;good enough&quot; and get Frankenstein mash-up songs that have no coherent &quot;flow&quot; or &quot;progression&quot; as its actually chunks of &quot;similar sounding songs&quot; not a coherent &quot;full song generation&quot; by AI but editing result of multiple chunks merged into something.
评论 #43257405 未加载
zaptrem3 months ago
One thing I&#x27;ve been thinking about is how to do a better hobbyist plan system. It would be cool to do a flat rate unlimited plan, but we wouldn&#x27;t want that to then be abused by larger customers&#x2F;companies. Are there existing API providers you think solve this particularly well?
评论 #43245482 未加载
评论 #43244910 未加载
weberer3 months ago
So if I make a song using this API, who owns the copyright? Is it me or Sonauto?
评论 #43246728 未加载
评论 #43246701 未加载
amarant2 months ago
This is pretty cool! It&#x27;s noticeably better than any of the other similar music generation tools I&#x27;ve tried, kudos!
column2 months ago
This looks pretty cool to integrate in hobby projects, however after creating an account via Google, clicking &quot;Payment portal&quot; shows this error :<p>Error creating billing portal Failed to create billing portal session: No configuration provided and your live mode default configuration has not been created. Provide a configuration or create your default by saving your customer portal settings in live mode at <a href="https:&#x2F;&#x2F;dashboard.stripe.com&#x2F;settings&#x2F;billing&#x2F;portal" rel="nofollow">https:&#x2F;&#x2F;dashboard.stripe.com&#x2F;settings&#x2F;billing&#x2F;portal</a>.<p>Also when trying to update my profile picture :<p>Failed to update image! column users.current_period_end does not exist
评论 #43264478 未加载
duped2 months ago
I would encourage everyone who thinks &quot;I want to apply AI to music&quot; to look at the existing problems that creators have, talk to them, and work to bring new products to market instead of things that devalue their work.<p>&quot;Generate a rock song&quot; is not a problem that working musicians have. &quot;Take this riff I recorded with whatever guitar I have in the studio and show me what it sounds like as a Les Paul through a 5150 or Strat through a AC30&quot; <i>is</i>, though.
评论 #43257502 未加载
评论 #43259196 未加载
lcolucci3 months ago
The transition btw two songs demo is super cool! I often need to do this when editing videos but used to have no way to do it.<p>Not to mention that now you can have playlists that transition seamlessly btw two songs. Low-cost party DJ?
echelon3 months ago
I&#x27;m familiar with video and image diffusion model architectures, but know almost nothing about music models.<p>Are there any good papers or writeups on them?<p>Are there any open source implementations to play with?
评论 #43246282 未加载
easyThrowaway3 months ago
I&#x27;m not going to comment on the technical side of things, which is way beyond my technical comprehensions skills, and I&#x27;m sure it required a considerable amount of brain, time and energy to reach similar results.<p>But music production and distribution is (actually, <i>was</i>) my home turf, so here&#x27;s my two cents on the topic:<p>I&#x27;ve already heard music qualitatively on par with the tracks available on your demo page. I&#x27;ve heard it way more than I truly wanted or felt it was necessary, at least once a day while tracking on pro tools hundreds of albums you&#x27;ve never ever heard of, in studios in France and LA, for years.<p>It was made with people with the best intentions, coming from all sorts of walks of life, and yet it was obvious from the first note they played that they were condemned to the oblivion, their music destined to be basically never heard by anyone.<p>And this has been done every day, multiple times a day, in every studio around the world, since the &#x27;60s.<p>20% of Spotify music has never been played once. IIRC less than 40% has been played more than once.<p>There&#x27;s a genuinely humbling scene in the 2002 documentary &quot;Scratch&quot; where DJ Shadow, a world-renowed DJ and producer, wades trough stacks of EPs out of a record store in NY that have never, ever been played once[1], which perfectly captures how little of the musical output being recorded we actually get to listen to.<p>Making music is very easy. Making music people want to listen to is hard, mind-bogglingly so. For every whitebread pop track you&#x27;ve heard on the radio, there&#x27;s thousands of other similar tracks that have been discarded by an A&amp;R, a radio DJ, some label, or simply by the audience.<p>I&#x27;m saying this with no ill feelings towards you or your work, but I can&#x27;t concieve even the flimsiest of reasons why anyone would ever listen to (or license&#x2F;sync&#x2F;track&#x2F; ) any of those generated songs once the novelty of &quot;music made by the AI&quot; is gone.<p>[1]<a href="https:&#x2F;&#x2F;www.youtube.com&#x2F;watch?v=1gpKYnRdf0A&amp;t=6s" rel="nofollow">https:&#x2F;&#x2F;www.youtube.com&#x2F;watch?v=1gpKYnRdf0A&amp;t=6s</a>
评论 #43247863 未加载
评论 #43248017 未加载
评论 #43253702 未加载
评论 #43250435 未加载
评论 #43250526 未加载
评论 #43250186 未加载
JoeDaDude2 months ago
Why is it &quot;music for developers&quot;? I was expecting one of those Lofi music videos designed to enhance concentration or similar. These are typically instrumentals, ostensibly because they are less distracting, something like this:<p><a href="https:&#x2F;&#x2F;www.youtube.com&#x2F;watch?v=M5QY2_8704o" rel="nofollow">https:&#x2F;&#x2F;www.youtube.com&#x2F;watch?v=M5QY2_8704o</a>
评论 #43249478 未加载
sid-the-kid3 months ago
Okay. I know these guys IRL. BUT, I genuinely think they have the best music model out there. Hands down. The songs are just more unique, and have a wider range of musical variation. With Suno&#x2F;Udio, the songs just sounds the same after a while (just with different lyrics).<p>That could just be me though. I am curious what users of Udio&#x2F;Suno think?
评论 #43248520 未加载
modeless2 months ago
By far the best use case here is generating &quot;Weird Al&quot; style parody covers of pop songs by just changing the lyrics. Songs that everyone knows but with custom lyrics are way more interesting than songs nobody has heard before generated at random.
r6182 months ago
i&#x27;ve been occasionally trying to get some usable ambience tracks from these various models, but none of them seem to be able to produce looping tracks<p>based on results so far it also looks like more flexible approach to ai generation would be to generate set of stems&#x2F;samples based on user description and let them to actually compose instead of producing complete audio (maybe this is already happening somewhere)<p>- in either case, properly looped tracks will be most likely necessary to be produced by these models at some point
评论 #43257598 未加载
评论 #43252283 未加载
covi3 months ago
Congrats on the API launch (from SkyPilot)!
评论 #43246889 未加载
naltroc3 months ago
how did you create this without committing grand theft musica
评论 #43244702 未加载
评论 #43244665 未加载
评论 #43246707 未加载
nlh2 months ago
This is super cool! Thanks for the hard work you&#x27;ve clearly put into this.<p>My dream product in this space (...that I didn&#x27;t know existed until I discovered your site about 10 minutes ago LOL):<p>I listen to music when I work&#x2F;code, and I used to loooooove Spotify Playlist Radio (a feature the reason for which they killed I will never understand) because it helped me discover new music in the style of music I already enjoyed working to. Liked a song? Add it to the seed list and click play to fine-tune the radio station.<p>So what I really want is just a fine-tuneable infinite stream of novel music to work to. And by fine-tuneable, I mean I&#x27;d love to be able to nudge the generation (Pandora style) with thumbs ups &#x2F; thumbs downs, or other more specific guidance&#x2F;feedback (more bass, faster tempo, etc.) until I have this perfectly crafted, customized-for-me stream of music.<p>I&#x27;d probably listen to it all day and happily pay $$ for this.<p>Is this a pipe dream?
评论 #43251946 未加载
unraveller2 months ago
The movie Electric Dreams is now the most prescient &#x27;80s movie about gen AI so far; An architect builds an approximation engine on his home PC which then ingests the whole internet&#x2F;TV and learns to compose music for the cute girl next door who plays the cello. Song mis-attribution is the central theme. The hit song from the movie Together In Electric Dreams is actually from the perspective of the gen AI choosing to self-destruct as a final show of his love. <a href="https:&#x2F;&#x2F;www.youtube.com&#x2F;watch?v=kDV-_q-iaK8" rel="nofollow">https:&#x2F;&#x2F;www.youtube.com&#x2F;watch?v=kDV-_q-iaK8</a><p>I bring it up only to provide a bit of balance to the soulless slop debate, proving creators can have diverging opinions on what is good in music creation and life—they don&#x27;t all feel threatened by poor substitutes no one can possibly enjoy.
toisanji3 months ago
how is this better or different from suno besides api? I&#x27;m assuming since you are smaller the quality is not as good and the depth not as wide.
评论 #43244429 未加载
评论 #43246484 未加载
zoogeny3 months ago
Not related to this post, but I was wondering about AI music generators and I don&#x27;t have experience with their capabilities. The ones I know seem catered to making entire songs.<p>I was having a discussion with a friend who writes a lot of guitar music but can also play bass and sing. However, getting good drums is a problem. What he&#x27;d like is a service to upload his songs in some form (just guitar, or a mixed version with bass and vocals) and get an output that layers a drum track without altering the input. Ideally with appropriate fills, etc. I mean, just getting an in-time drum stem would probably be even better.<p>Is there any GenAI service to do this kind of incremental additive drums?
评论 #43245709 未加载
评论 #43245649 未加载
aczerepinski2 months ago
Creating music is the most rewarding thing I’ve found in life, and I can’t wrap my head around why anyone would want to automate that away.<p>Less of this, more robots they do my dishes please.
评论 #43259692 未加载
jtreminio2 months ago
You need an OpenApi spec!
skeptrune2 months ago
Honestly pretty cool. I&#x27;m curious how easy it will be for different video platforms and editors to work it in as a feature or maybe plugin
moreiarty2 months ago
ah sweet man-made horrors beyond comprehension
tombot3 months ago
What is the point of generating this low quality AI slop music, what real use case do you have in mind?
评论 #43244844 未加载
评论 #43245059 未加载
评论 #43244790 未加载
评论 #43257713 未加载
jdee3 months ago
Signed up with gmail, and get &#x27;Generation Failed&#x27; with every attempt. Please dont email me or add me to your marketing list.
评论 #43246868 未加载
iamsaitam2 months ago
Without disclosing your training data, this should be considered piracy and removed from HN.
评论 #43253689 未加载