# Separate Speakers in Audio

Pull apart multi-voice recordings into individual tracks for easier editing or captioning. Send an existing episode or upload URL to `/content/SeparateSpeakersAudio` and AutoContent delivers isolated files per speaker.

## Step 1: Submit the Separation Request

```bash
curl -X POST "https://api.autocontentapi.com/content/SeparateSpeakersAudio" \
  -H "Authorization: Bearer YOUR_API_TOKEN" \
  -H "Content-Type: application/json" \
  -d '{
    "audioUrl": "https://storage.autocontentapi.com/audio/panel-discussion.mp3",
    "callbackData": "separate-speakers-run-001"
  }'
```

**Parameters**

* `audioUrl` *(required)*: Publicly accessible audio file or existing episode URL.
* `callbackData` *(optional)*: String returned with webhook notifications so you can reconcile jobs.

See [Track Requests & Status Codes](https://docs.autocontentapi.com/quick-start/tools/track-requests) for the shared polling flow and request lifecycle.

## Step 2: Monitor Status

Track the request using the returned `request_id`:

```bash
curl -X GET "https://api.autocontentapi.com/content/Status/YOUR_REQUEST_ID" \
  -H "Authorization: Bearer YOUR_API_TOKEN"
```

Once processing finishes (`status` = `100`), the status response contains fresh download links for each isolated voice along with the consolidated mix and transcript text (when available).

## Tips

1. **Upload clean sources** – If needed, re-export the episode without background music to maximize accuracy.
2. **Name webhooks clearly** – Combine `callbackData` with internal IDs so you can map results back to your CMS.
3. **Pair with transcription** – Feed the isolated tracks into [Transcribe Audio](https://docs.autocontentapi.com/quick-start/tools/transcribe-audio) for speaker-labelled captions.