pedalboard VS jukebox

spotify/pedalboard: audio effects for Python and TensorFlow

pip install git+https://github.com/spotify/pedalboard.git

I haven't tried it yet, but pedalboard is probably your best bet. DawDreamer also looks interesting ...

I found this really cool and promising library called "Pedalboard" but when I try to install it using PIP I get this error message:

Perhaps Spotify Pedalboard might be of interest

pedalboard – A Python library for manipulating audio

Thanks for the suggestions, everybody! I'm going to try writing a python script using this library: https://github.com/spotify/pedalboard to loop through all files in my sample directory and save the processed outputs to a new folder. Hoping it doesn't melt my poor 2018 Macbook Pro - I'll try running it on a smaller folder at first and see how it goes.

Do you want to run the effect online or offline? You can do it offline with: https://github.com/spotify/pedalboard

I think you could do it with this https://github.com/spotify/pedalboard

openai/jukebox: Music Generation

https://github.com/openai/jukebox The demo code is there.

I didn't even know about it until I heard Sam Altman casually mention it in an interview, I was expecting some basic tunes generator, but this is so amazing! I mean yeah the voices are not clear, it's muffled, but look at how far have image models progressed, if you applied the same amount of collaborative effort here, the results could be amazing! ElevenLabs showed how good and clear can AI-created voices sound. The only reason I can think of is that the Jukebox code is under view license only.

OpenAI had this figured out 3 years ago: https://openai.com/blog/jukebox/ . You could then even define your own text. Model is open source too.

They've had jukebox for a few years now, so I'm sure some new model will get released and explode overnight, like what chatGPT did.

That already exists

This model is designed to output raw audio.

However, there are many models which do output midi. That's actually much simpler, and has been done already a few years ago.

I thought OpenAI did this. But then, I might misremember, because their Jukebox actually also seems to produce raw audio (https://openai.com/blog/jukebox/).

However, midi generation is so easy, you even find it in some tutorials: https://www.tensorflow.org/tutorials/audio/music_generation