Quickstart - AudioShake Developers

Make your first API call

  1. Create an account
    Sign up at dashboard.audioshake.ai. You’ll get 10 free credits to start building immediately.

  2. Create an API key
    In the dashboard, go to Settings > API Keys and click Create new key. Copy and store the key — you will not be able to view it again.

  3. Create your first Task
    A Task runs one or more models against a media source. This example separates a track into vocals and instrumental:

    curl -X POST "https://api.audioshake.ai/tasks" \
  -H "Content-Type: application/json" \
  -H "x-api-key: your_api_key" \
  -d '{\n       "url": "https://demos.audioshake.ai/demo-assets/shakeitup.mp3",\n       "targets": [\
      { "model": "vocals", "formats": ["wav"] },\
      { "model": "instrumental", "formats": ["wav"] }\
    ]\n     }'

   import requests

response = requests.post(
       "https://api.audioshake.ai/tasks",
       headers={
           "Content-Type": "application/json",
           "x-api-key": "your_api_key"
       },
       json={
           "url": "https://demos.audioshake.ai/demo-assets/shakeitup.mp3",
           "targets": [\
               {"model": "vocals", "formats": ["wav"]},\
               {"model": "instrumental", "formats": ["wav"]}\
           ]
       }
   )
   
   print(response.json()["id"])

   const response = await fetch("https://api.audioshake.ai/tasks", {
     method: "POST",
     headers: {
       "Content-Type": "application/json",
       "x-api-key": "your_api_key"
     },
     body: JSON.stringify({
       url: "https://demos.audioshake.ai/demo-assets/shakeitup.mp3",
       targets: [\
         { model: "vocals", formats: ["wav"] },\
         { model: "instrumental", formats: ["wav"] }\
       ]
     })
   });
   
   const task = await response.json();
   console.log(task.id);

Save the id from the response.

  1. Check Task status
    Tasks process asynchronously. Poll until each target’s status is completed or error:

    curl "https://api.audioshake.ai/tasks/<task-id>" \
  -H "x-api-key: your_api_key"

    task = requests.get(
    f"https://api.audioshake.ai/tasks/{task_id}",
    headers={"x-api-key": "your_api_key"}
).json()

for target in task["targets"]: print(f"{target['model']}: {target['status']}")

const res = await fetch(https://api.audioshake.ai/tasks/${taskId}, { headers: { "x-api-key": "your_api_key" } }); const task = await res.json();

for (const target of task.targets) { console.log(${target.model}: ${target.status}); }


Each completed target includes an `output` array with download links.

Output download links expire after one hour. Download and store files in your own storage.

Use [webhooks](https://developer.audioshake.ai/api-reference/tasks/webhooks) to get notified when targets complete instead of polling.

## Using a local file

Upload your file first with [Upload File](https://developer.audioshake.ai/api-reference/assets/upload), then use the returned `assetId` instead of `url`:

```json
{
  "assetId": "your_asset_id",
  "targets": [\
 { "model": "vocals", "formats": ["wav"] },\
 { "model": "instrumental", "formats": ["wav"] }\
  ]
}

What’s next?

Models \
Browse all available models.

Instrument Separation \
Isolate vocals, drums, bass, and more.

Webhooks \
Get notified when targets complete instead of polling.

API Reference \
Full endpoint reference.