> ## 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.

# Lyric Transcription

> Generate time-synced lyrics from a song

Extract word- and line-level timestamped lyrics from a song. Use the output for karaoke rendering, subtitle generation, music search, or analytics.

## Create a Task

<CodeGroup>
  ```python transcribe_lyrics.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": "transcription", "formats": ["json"]}
          ]
      }
  )

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

  ```javascript transcribeLyrics.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: "transcription", 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": "transcription", "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.

<Tip>Use clean, full-length source audio for best results. Heavily compressed or low-bitrate files reduce transcription accuracy.</Tip>

<Note>Need **word-level timing** for karaoke or subtitles? Use the `alignment` model instead — it provides precise per-word timestamps. See [Models](/models#lyric-transcription) for details.</Note>

## Use cases

* Render karaoke-style highlighted lyrics in real time
* Convert to SRT or VTT subtitle formats
* Build searchable lyric databases with per-line timestamps
* Power lyric-synced visual experiences

<CardGroup cols={2}>
  <Card title="Build Karaoke Tracks" icon="microphone-lines" href="/create-karaoke-tracks">
    Combine lyric transcription with stem separation.
  </Card>

  <Card title="Models" icon="grid-2" href="/models">
    See all available transcription and alignment models.
  </Card>
</CardGroup>