# 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](/quick-start/tools/track-requests.md) 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](/quick-start/tools/transcribe-audio.md) for speaker-labelled captions.


---

# Agent Instructions: Querying This Documentation

If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter:

```
GET https://docs.autocontentapi.com/quick-start/tools/separate-speakers-audio.md?ask=<question>
```

The question should be specific, self-contained, and written in natural language.
The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.