> ## 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.

# Multi-Speaker Separation

> Isolate individual speakers from a mixed multi-speaker recording

Separate a recording with multiple speakers into one stem per speaker — even when speakers overlap. Use the outputs for transcription, speaker-specific editing, or feeding clean single-speaker audio into downstream AI models.

## Create a Task

<CodeGroup>
  ```python multi_speaker.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": "multi_voice", "formats": ["wav"]}
          ]
      }
  )

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

  ```javascript multiSpeaker.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: "multi_voice", formats: ["wav"] }
      ]
    })
  });

  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": "multi_voice", "formats": ["wav"] }
      ]
    }'
  ```
</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.

The model outputs one audio file per detected speaker. Even when speakers overlap, each stem contains only the isolated voice of a single speaker.

## Use cases

* Clean per-speaker audio for transcription and diarization
* Isolate individual voices in meetings, interviews, or panel discussions
* Prepare training data for speech AI models
* Enable speaker-specific editing in podcast post-production

<CardGroup cols={2}>
  <Card title="Speech Recovery" icon="waveform-lines" href="/speech-recovery">
    Denoise and de-reverb individual speaker stems after separation.
  </Card>

  <Card title="Dialogue Separation" icon="film" href="/remove-dialogue-for-dubbing">
    Separate all speech from music and effects instead.
  </Card>
</CardGroup>