andreasjansson / synth-one-liner

Generate "algorithmic symphony" one-liners with grammar-constrained CodeLlama

Cold

Public
206 runs
L40S
GitHub

Run with an API

Playground API Examples README Versions

Input

Run this model in Node.js with one line of code:

npx create-replicate --model=andreasjansson/synth-one-liner

or set up a project from scratch

Install Replicate’s Node.js client library:

npm install replicate

Set the REPLICATE_API_TOKEN environment variable:

export REPLICATE_API_TOKEN=<paste-your-token-here>

Find your API token in your account settings.

Import and set up the client:

import Replicate from "replicate";

const replicate = new Replicate({
  auth: process.env.REPLICATE_API_TOKEN,
});

Run andreasjansson/synth-one-liner using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

const output = await replicate.run(
  "andreasjansson/synth-one-liner:3b1b5e4f56195294d13b72556c56593e9a88f69264909b5d2636e1b5336cdea7",
  {
    input: {
      duration: 60
    }
  }
);

console.log(output);

To learn more, take a look at the guide on getting started with Node.js.

Install Replicate’s Python client library:

pip install replicate

Set the REPLICATE_API_TOKEN environment variable:

export REPLICATE_API_TOKEN=<paste-your-token-here>

Find your API token in your account settings.

Import the client:

import replicate

Run andreasjansson/synth-one-liner using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "andreasjansson/synth-one-liner:3b1b5e4f56195294d13b72556c56593e9a88f69264909b5d2636e1b5336cdea7",
    input={
        "duration": 60
    }
)
print(output)

To learn more, take a look at the guide on getting started with Python.

Set the REPLICATE_API_TOKEN environment variable:

export REPLICATE_API_TOKEN=<paste-your-token-here>

Find your API token in your account settings.

Run andreasjansson/synth-one-liner using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

curl -s -X POST \
  -H "Authorization: Bearer $REPLICATE_API_TOKEN" \
  -H "Content-Type: application/json" \
  -H "Prefer: wait" \
  -d $'{
    "version": "3b1b5e4f56195294d13b72556c56593e9a88f69264909b5d2636e1b5336cdea7",
    "input": {
      "duration": 60
    }
  }' \
  https://api.replicate.com/v1/predictions

To learn more, take a look at Replicate’s HTTP API reference docs.

Output

audio

Video Player is loading.

Current Time 00:00:000

Duration 00:00:000

Loaded: 0%

Stream Type LIVE

Remaining Time 00:00:000

sample_expression

sample=(t*((t>>9)|(t>>13)))^((t>>10)&457)

Generated in

2.2 seconds

Tweak itReport

This output was created using a different version of the model, andreasjansson/synth-one-liner:22869a12.

Run time and cost

This model runs on Nvidia L40S GPU hardware. We don't yet have enough runs of this model to provide performance information.

Readme

Synth one-liner

In 2011 Viznut posted a blog post called “Algorithmic symphonies from one line of code – how and why?”. He described a way to generate algorithmic 8-bit synth compositions in a single line of C. For example,

main(t){for(t=0;;t++)putchar(t*(((t>>12)|(t>>8))&(63&(t>>4))));}

You’d compile that program and pipe it to your soundcard, and it would play an ever-evolving piece of noise music.

This is so fucking cool. That little equation t*(((t>>12)|(t>>8))&(63&(t>>4))) will tweak the bits of the value of the current time step as a kind of chaos process that actually sounds great!

I wanted to see if I could do that automatically.

Automatic one-liners

Using CodeLlama 7B I make a prompt with a bunch of one-liners from IRC.

I then use Llama.cpp’s grammar decoder to constrain the output to valid one-liners. Those one-liners are then evaluated and converted to audio.

Cover image by https://replicate.com/yash-banka/moon