I’ve transcribed hundreds of hours of guitar music over 25+ years, using the method described in this article. It was such a slog that I ended up creating tool to help streamline the process: Soundslice (https://www.soundslice.com/).
It combines audio playback directly with a tab editor, so that you can immediately write down what you’ve figured out and your transcription stays in sync with the original audio. This makes transcribing incredibly fast and (importantly) accurate.
It’s got audio slowdown, precise looping, “synth overlay” (playback of the transcription and original audio at the same time, to spot errors), auto stem separation and a full-featured tab/notation editor with support for hundreds of notations.
When you’re done, you get a very useful artifact: a synced transcription, effectively a bespoke practice environment for that piece of music.
Over the years, Soundslice has expanded into a lot more than a pure transcription tool, but lots of people still use it for its original intended purpose. (It supports any instrument that uses western music notation, not just guitar.) If you’re at all interested in transcribing music, give it a shot.
I'm actually trying to build something similar to this for personal use, not as a product. What did you find was the most difficult technical step when building? I'm finding it particularly challenging to separate rhythm and lead guitar parts (both in terms of stem separation and also when transcribing by ear).
I've been working on it full-time since 2012, so it's hard for me to reduce 14 years' worth of work to a single "most difficult technical step."
Sorry, I don't mean to be rude or unhelpful, but that's not a question I can provide a meaningful answer to. There have been dozens, probably hundreds, of difficult technical challenges in building Soundslice.
Hey, just wanted to say I really love your software and it was a pleasure finding out that you guys are active on HN (I remember your ASCII tabs post). It's very pleasant to use, especially with the sync mode to help play over tabs I have with the official music video. Cheers
I just recently discovered Soundslice after decades of transcribing with various tools and libraries. They worked butyour tool puts everything together so well. Immediately subscribed. Thank you for making this tool. Cheers.
How have i never heard about this, will definitely give a try.
What about a DAW integrated transcription tool, as a VST maybe, is it too niche? This is something i always wanted and never really found in the capacity i needed, essentially doing what soundslice does both track per track and also having the full score, most tools available try to convert to midi via usual methods or do some mumbo-jumbo AI to write the score. Since 90% of recording musicians time is spent on a DAW and sometimes having everything in the box streamlines the work a lot.
Ah! Looks like Drumeo (part of Musora) uses Soundslice as their transcription tool? The UI of the demos exactly matches what I'm used to seeing in Drumeo.
Hi, I make that site! We don't have any "basic effects like normalization/compression," so I think you may be mistaking us for something else?
Soundslice is oriented around sheet music that's synced with audio. So while we have a few audio-processing features (basic cropping, slowdown and fine-grained pitch correction), that stuff is all secondary to the notation aspect.
Thanks for sharing this. Your site is great. I've already learned a bunch of stuff, just browsing around the existing submissions.
I had a chuckle pondering whether you A/B tested "really freaking cool-looking" versus "really cool-looking" in the prompt. What a weird world we live in! :-)
Lol - I had a much fancier prompt to start, with things like "Be sure to invoke your frontend-designer skill" and "Make at least one applet inside the page with user-friendly controls".
But then I said screw it, let me try "really freaking cool"
Interpreting sheet music images is very complex, and I’m not surprised general-purpose LLMs totally fail at it. It’s orders of magnitude harder than text OCR, due to the two-dimensional-ness.
Obviously it will depend on what you're doing and one's tolerance for things many deem to be annoying. I've encountered people with incredibly high tolerance for slow and awkward workflows but, alas, I am not one of them.
If I had to call out one thing it would be that you can't do tests without having a database there. This results in incredibly slow tests for even the simplest things. I don't need to test database persistence every time I'm testing some domain logic. So maybe then don't do fat models and "map" the data from Django models to a domain layer? Well, congrats, you've just manually implemented a data mapper ORM, which is what SQLAlchemy is.
It works well for simple CRUD stuff, which is really useful. But it very quickly becomes a mess and a big ball of mud when you start to do more complicated things. IMO a db access layer or web framework should be completely independent of domain logic, but Django makes that really difficult.
> IMO a db access layer or web framework should be completely independent of domain logic, but Django makes that really difficult.
That is an issue/features in Django, depending on your view. You really don't get to do things the framework doesn't want. If you're trying to fight the ORM or any of the components in Django really, including the Django REST framework, you're going to lose and have a bad time.
There are certainly reason why you'd want to separate domain logic from the database access, but then Django isn't what you want. You're also going to miss out many of the things that makes Django easy to work with, like getting most CRUD operations for free.
I don't fully understand your comment, but Soundslice has had first-class support for tablature for more than 10 years now. There's an excellent built-in tab editor, plus importers for various formats. It's just the ASCII tab support that's new.
I’m not super familiar with Soundslice. But all the tab users I know use guitar pro or maybe ultimate guitar, and none of them can read standard notation on its own. Does Soundslice have a lot of tab-first users?
Yes, Soundslice has a ton of tab-first users. And in fact the primary reason I founded the site was to scratch my own itch of being able to create tab that's synced with real audio recordings. (I'm a guitarist myself.)
When I read the blog post, I thought it was saying that Soundslice didn't have any tab support.
The comparison of "we expect this (classical notation screenshot) but instead got this (ascii tab screenshot)" made me think that the only thing Soundslice supported was classical notation.
Definitely a subtle distinction there. Soundslice supports tab in many formats (MusicXML, Guitar Pro, PowerTab, TuxGuitar, PDF/images of published tab, or tab notated directly in the Soundslice editor) but didn't support ASCII format yet.
I wonder if LLMs will stimulate ASCII formats for more things, and whether we should design software in general to be more textual in order to work better with LLMs.
I've had AI create ascii-art (Nethack-style) dungeon diagrams when I asked it to write me a D&D adventure. Last time I tried it these dungeon diagrams were completely nonsensical, but that was a few years ago.
I think ASCII art in particular is generally a weak point for LLMs; maybe they could do better if they used an image model. Other ASCII syntaxes using matched { } delimiters seem like they would be easier.
Just a quick plug: check out Soundslice. It's interactive sheet music with a ton of learning tools built in, including easy navigation, looping, tempo changing and transposition.
We've also got a scanning feature that does OCR for sheet music, to get music into our system. Plus there's a full-featured notation editor. A good overview is at https://www.soundslice.com/features/
It combines audio playback directly with a tab editor, so that you can immediately write down what you’ve figured out and your transcription stays in sync with the original audio. This makes transcribing incredibly fast and (importantly) accurate.
It’s got audio slowdown, precise looping, “synth overlay” (playback of the transcription and original audio at the same time, to spot errors), auto stem separation and a full-featured tab/notation editor with support for hundreds of notations.
When you’re done, you get a very useful artifact: a synced transcription, effectively a bespoke practice environment for that piece of music.
Over the years, Soundslice has expanded into a lot more than a pure transcription tool, but lots of people still use it for its original intended purpose. (It supports any instrument that uses western music notation, not just guitar.) If you’re at all interested in transcribing music, give it a shot.
reply