Create Sonic-Themed Music with the fofr/musicgen-sonic Cognitive Actions

21 Apr 2025
Create Sonic-Themed Music with the fofr/musicgen-sonic Cognitive Actions

In the ever-evolving world of music technology, the ability to generate high-quality audio that captures unique themes can greatly enhance user experiences. The fofr/musicgen-sonic API offers a powerful Cognitive Action to generate music inspired by the iconic Sonic the Hedgehog 2 game. By leveraging the fine-tuned MusicGen model, developers can create captivating soundscapes by simply defining a few parameters. This article will explore how to integrate this action into your applications, providing a comprehensive guide for getting started.

Prerequisites

Before diving into the integration, ensure you have the following:

  • An API key for the Cognitive Actions platform.
  • Familiarity with making HTTP requests and handling JSON payloads.
  • A Python environment set up for testing the API calls.

For authentication, you’ll typically pass your API key in the request headers. This will allow you to securely interact with the Cognitive Actions API.

Cognitive Actions Overview

Generate Sonic Themed Music

Description: This action generates music inspired by Sonic the Hedgehog 2, utilizing the MusicGen model to produce high-quality audio based on user-defined parameters and optional input audio.

Category: Music Generation

Input

The action accepts a variety of parameters, allowing for detailed customization. Below is a breakdown of the input schema:

  • seed (integer): Specifies the random seed for variability. Default is None or -1 for a random seed.
  • topK (integer): Limits the sampling to the top k most likely tokens. Default is 250.
  • topP (number): Restricts sampling based on cumulative probability. Default is 0 (using top_k).
  • prompt (string): Describes the type of music to be generated. Example: "16bit sonic video game music".
  • duration (integer): Length of the generated audio in seconds. Default is 8.
  • audioInput (string, URI): A URI to an audio file that influences the generated music.
  • temperature (number): Controls sampling diversity. Default is 1.
  • continuation (boolean): If true, the output continues from the end of the input audio. Default is false.
  • outputFormat (string): Format of the generated audio, either "wav" or "mp3". Default is "wav".
  • customWeights (string): Model weights to use for MusicGen. Leave blank to use defaults.
  • multiBandDiffusion (boolean): If true, employs MultiBand Diffusion for non-stereo models. Default is false.
  • continuationEndTime (integer): End time for audio continuation. Default is -1 (end of clip).
  • continuationStartTime (integer): Start time of the audio for continuation. Default is 0.
  • normalizationStrategy (string): Method for normalizing audio. Default is "loudness".
  • classifierFreeGuidance (integer): Adjusts input influence on outputs. Default is 3.

Example Input:

{
  "topK": 250,
  "topP": 0,
  "prompt": "16bit sonic video game music",
  "duration": 8,
  "temperature": 1,
  "continuation": false,
  "outputFormat": "wav",
  "continuationStartTime": 0,
  "normalizationStrategy": "loudness",
  "classifierFreeGuidance": 3
}

Output

The action returns a URL pointing to the generated audio file. An example output could look like:

Example Output:

https://assets.cognitiveactions.com/invocations/798298b4-cd58-4050-a9ea-d6c9c8d773f1/bf8c0cec-5e0a-4de5-8b05-4ca541e50aec.wav

Conceptual Usage Example (Python)

Below is a conceptual example of how a developer might integrate the Generate Sonic Themed Music action within a Python application:

import requests
import json

# Replace with your Cognitive Actions API key and endpoint
COGNITIVE_ACTIONS_API_KEY = "YOUR_COGNITIVE_ACTIONS_API_KEY"
COGNITIVE_ACTIONS_EXECUTE_URL = "https://api.cognitiveactions.com/actions/execute" # Hypothetical endpoint

action_id = "0902cd2c-c967-42e3-9480-abc40f18b3c5" # Action ID for Generate Sonic Themed Music

# Construct the input payload based on the action's requirements
payload = {
    "topK": 250,
    "topP": 0,
    "prompt": "16bit sonic video game music",
    "duration": 8,
    "temperature": 1,
    "continuation": False,
    "outputFormat": "wav",
    "continuationStartTime": 0,
    "normalizationStrategy": "loudness",
    "classifierFreeGuidance": 3
}

headers = {
    "Authorization": f"Bearer {COGNITIVE_ACTIONS_API_KEY}",
    "Content-Type": "application/json"
}

try:
    response = requests.post(
        COGNITIVE_ACTIONS_EXECUTE_URL,
        headers=headers,
        json={"action_id": action_id, "inputs": payload} # Hypothetical structure
    )
    response.raise_for_status() # Raise an exception for bad status codes (4xx or 5xx)

    result = response.json()
    print("Action executed successfully:")
    print(json.dumps(result, indent=2))

except requests.exceptions.RequestException as e:
    print(f"Error executing action {action_id}: {e}")
    if e.response is not None:
        print(f"Response status: {e.response.status_code}")
        try:
            print(f"Response body: {e.response.json()}")
        except json.JSONDecodeError:
            print(f"Response body: {e.response.text}")

In this snippet, replace YOUR_COGNITIVE_ACTIONS_API_KEY with your actual API key. The payload structure showcases how to configure the parameters for generating the Sonic-themed music. The endpoint URL and request structure are illustrative and should be adapted as necessary.

Conclusion

The fofr/musicgen-sonic Cognitive Action enables developers to create engaging audio experiences inspired by the Sonic franchise. By utilizing the various input parameters, you can customize the music generation process to fit the needs of your application. Start integrating this powerful action today to bring your projects to life with unique soundscapes!

← Back to All Articles