> ## Documentation Index
> Fetch the complete documentation index at: https://developer.audioshake.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# Build Karaoke Tracks

> Create karaoke-ready outputs with stem separation and lyric transcription in a single request

Build a complete karaoke package in one API call — an instrumental backing track, a vocal reference, and time-synced lyrics. All three models run in parallel from a single Task.

## Create a Task

<CodeGroup>
  ```python build_karaoke.py theme={null}
  import requests

  API_KEY = "your_api_key"
  HEADERS = {"Content-Type": "application/json", "x-api-key": API_KEY}

  response = requests.post(
      "https://api.audioshake.ai/tasks",
      headers=HEADERS,
      json={
          "assetId": "your_asset_id",
          "targets": [
              {"model": "instrumental", "formats": ["wav"]},
              {"model": "vocals", "formats": ["wav"]},
              {"model": "alignment", "formats": ["json"]}
          ]
      }
  )

  task_id = response.json()["id"]
  print(f"Task created: {task_id}")
  ```

  ```javascript buildKaraoke.js theme={null}
  const API_KEY = "your_api_key";
  const headers = { "Content-Type": "application/json", "x-api-key": API_KEY };

  const createRes = await fetch("https://api.audioshake.ai/tasks", {
    method: "POST",
    headers,
    body: JSON.stringify({
      assetId: "your_asset_id",
      targets: [
        { model: "instrumental", formats: ["wav"] },
        { model: "vocals", formats: ["wav"] },
        { model: "alignment", formats: ["json"] }
      ]
    })
  });

  const { id: taskId } = await createRes.json();
  console.log(`Task created: ${taskId}`);
  ```

  ```bash curl theme={null}
  curl -X POST "https://api.audioshake.ai/tasks" \
    -H "Content-Type: application/json" \
    -H "x-api-key: $AUDIOSHAKE_API_KEY" \
    -d '{
      "assetId": "your_asset_id",
      "targets": [
        { "model": "instrumental", "formats": ["wav"] },
        { "model": "vocals", "formats": ["wav"] },
        { "model": "alignment", "formats": ["json"] }
      ]
    }'
  ```
</CodeGroup>

[Check Task status](/check-task-status) to monitor progress and download results, or use [webhooks](/api-reference/tasks/webhooks) to be notified when each target completes.

## Outputs

| Target             | Role                                       |
| ------------------ | ------------------------------------------ |
| `instrumental`     | Backing track for playback                 |
| `vocals`           | Reference track for QA and timing          |
| `alignment` (JSON) | Word-level timed text for on-screen lyrics |

## Use cases

* Power karaoke apps with synced lyrics and backing tracks
* Publish sing-along experiences on streaming platforms
* Batch-process entire song catalogs for karaoke libraries

<CardGroup cols={2}>
  <Card title="Stem Separation" icon="waveform-lines" href="/separate-stems">
    Extract additional individual instruments beyond vocals.
  </Card>

  <Card title="Lyric Transcription" icon="file-lines" href="/transcribe-lyrics">
    Learn more about the transcription model and output format.
  </Card>
</CardGroup>