> For the complete documentation index, see [llms.txt](https://docs.autocontentapi.com/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.autocontentapi.com/quick-start/tools/clone-voice.md).

# Clone a Voice

Capture a custom speaker and reuse that voice across podcasts, shorts, and other AutoContent tools.

## Before You Begin

* Add your API key in `Settings`; the voice cloning page requires authentication.
* Prepare a clean audio recording: at least 10 seconds, single speaker, minimal noise, MP3 or WAV, under 10 MB.
* Decide whether the source lives at a public HTTPS URL or on your machine.

## Step 1: Open the Voice Cloner

1. In the sidebar, go to `Tools -> Clone Voice` (`/tools/clone-voice`).
2. Confirm the banner shows your API key status before proceeding.

## Step 2: Choose the Input Method

Use the toggle at the top of the form to switch between:

* **URL** – Paste a direct HTTPS link to an MP3 or WAV file. The app validates the scheme and common extensions.
* **Upload File** – Select a local audio file. The uploader blocks files above 10 MB and anything that is not audio/\*.

## Step 3: Provide Voice Details

Fill in the required fields:

| Field        | Required | Notes                                                                     |
| ------------ | -------- | ------------------------------------------------------------------------- |
| Voice Name   | Yes      | Friendly label that appears in the voice pickers while creating episodes. |
| Audio Source | Yes      | Either a public URL or uploaded file depending on the selected mode.      |

Use the "Recording Requirements" callout as a checklist: clear speech, single speaker, and natural pacing produce the best clone.

## Step 4: Start the Clone Request

Select **Clone Voice**. The button locks while AutoContent submits the request and displays a success banner with the `request_id` once accepted. Typical processing time is 5-10 minutes.

Want to automate this outside the UI? Toggle **Show API Request** to expose the exact payload. Base requests look like:

```bash
# Clone from a hosted MP3 or WAV
curl -X POST "https://api.autocontentapi.com/content/CloneVoice" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "audioUrl": "https://cdn.example.com/voices/jordan-intro.mp3",
    "name": "Jordan Narrator"
  }'
```

```bash
# Clone from a local file
curl -X POST "https://api.autocontentapi.com/content/CloneVoice" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -F "audioFile=@/path/to/jordan-intro.wav" \
  -F "name=Jordan Narrator"
```

Responses include:

```json
{
  "request_id": "voice-clone-1234abcd",
  "status": 0
}
```

Track progress on the **Requests** page (`/requests`). When the status reaches `100`, the clone is ready for use.

## Step 5: Use the New Voice in Podcasts

* Open `Podcasts -> Episodes -> New Episode` and expand **Optional Settings**. The cloned voice appears in the voice selectors once processing completes.
* For API calls, run `GET /content/GetVoices` after the clone succeeds and copy the numeric `id` for the cloned voice. Send that number in `voice1`, `voice2`, or `voiceId`; do not send the display name.
* Update existing templates or schedulers to swap in the new voice for future productions.
* Visit the `Voices` page if you want to preview or rename the entry after it is created.

## Related Endpoints

* `POST /content/CloneVoice` – Start voice cloning from a file or URL.
* `GET /content/GetVoices` – List available voices, including custom clones.

## What's Next?

* Pair the cloned voice with fresh audio using [Create a Podcast Episode](/quick-start/podcasts/create-podcast-episode.md).
* Need more variety? Explore the built-in options in [Voices](/voices.md).
* Capture supporting research to feed that new host via [Start Deep Research](/quick-start/deep-researches/start-deep-research.md).