POST
/
Extraction
import requests
import json

url = "https://api.musicgpt.com/api/public/v1/Extraction"
headers = {
    "Authorization": "<API_KEY>",
    "accept": "application/json"
}

files = {
    "audio_file": open("path_to_audio.mp3", "rb")
}
data = {
    "audio_url": "",
    "stems": json.dumps(["vocals", "drums"]),
    "preprocessing_options": json.dumps(["Denoise"]),
    "webhook_url": "http://webhook.musicgpt.com"
}

response = requests.post(url, headers=headers, data=data, files=files)
print(response.json())
{
  "success": true,
  "task_id": "62725d68-01e8-4c87-8fb0-298aa81c529c",
  "conversion_id": "46b358c9-b22f-49d1-a68d-17901a6a549b",
  "eta": 11,
  "credit_estimate": 2.5
}

Extract data from an audio file or URL with an option to specify a webhook for callback.

​
🎧 Endpoint

POST /Extraction

This is the endpoint used for initiating extraction tasks from audio inputs.

​
🔢 Request Parameters

ParameterTypeRequiredDescription
audio_urlStringOptionalThe URL of an audio file to extract data from. Either audio_url or audio_file must be provided.
audio_fileUploadFileOptionalUpload the audio file directly. Either audio_url or audio_file must be provided.
webhook_urlStringOptionalCallback URL for async response.

💡 Note: You must provide either audio_url or audio_file — not both as None.

​
📤 Sample Request

​
🐚 cURL

curl -X POST "https://api.musicgpt.com/api/public/v1/Extraction" \
-H "accept: application/json" \
-H "Authorization: <api_key>" \
-F "audio_url=https://www.youtube.com/watch?v=jGflUbPQfW8" \
-F "webhook_url=http://webhook.musicgpt.com"

​
🐍 Python

import requests

url = "https://api.musicgpt.com/api/public/v1/Extraction"

headers = {
    "accept": "application/json",
    "Authorization": "<api_key>"
}

input_audio_file = open("{path_to_your_audio_file}", "rb")

payload = {
    "audio_url": "",
    "webhook_url": "http://abcd.requestcatcher.com/test"
}

response = requests.post(url=url,
                         headers=headers,
                         data=payload,
                         files={"audio_file": input_audio_file})

print(response.status_code, response.json())

🔐 Replace {path_to_your_audio_file}, api_key, and webhook_url before executing.

​
📥 Sample Response

​
✅ Success (200 OK)

{
  "success": true,
  "task_id": "62725d68-01e8-4c87-8fb0-298aa81c529c",
  "conversion_id": "46b358c9-b22f-49d1-a68d-17901a6a549b",
  "eta": 11
}

​
❌ Common Errors

  • 422 Unprocessable Entity: Both audio_url and audio_file cannot be None.
  • 500 Internal Server Error: An error occurred on the server.

​
📞 Webhook Response

When the extraction completes, the webhook receives:

{
  "success": true,
  "task_id": "62725d68-01e8-4c87-8fb0-298aa81c529c",
  "conversion_id": "46b358c9-b22f-49d1-a68d-17901a6a549b",
  "audio_path": "https://aws.signed.url",
  "vocal": "https://aws.signed.url/vocal",
  "instrumental": "https://aws.signed.url/instrumental",
  "back_vocal": "https://aws.signed.url/back_vocal",
  "conversion_cost": 5.0,
  "conversion_duration": 120.5
}

You can download or stream each audio layer from the respective URLs.

​
Payload and Request Formation

Authorizations

​
Authorization
string
header
required

Body

multipart/form-data

Response

200
application/json

Successfully initiated audio extraction

The response is of type object.