> ## Documentation Index
> Fetch the complete documentation index at: https://docs.play.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# Voice Cloning

> Learn how to create custom voices from your own audio samples

[Try Voice Cloning now](https://play.ai/voices/voice-clones?openCloneVoiceModal=true)

<Frame>
  <video autoPlay muted loop playsInline>
    <source src="https://mintcdn.com/playhtinc/oLfqv-LO9FzqCeTi/media/voice-cloning/video/voiceCloning.mp4?fit=max&auto=format&n=oLfqv-LO9FzqCeTi&q=85&s=fe0a08f177190dd6ebed8a761ffb5cb4" type="video/mp4" data-path="media/voice-cloning/video/voiceCloning.mp4" />
  </video>
</Frame>

<Tip>Know more about Voice Cloning here: [Play AI Voice Cloning](https://www.youtube.com/watch?v=nzyotTIk060)</Tip>

## Steps to create your voice clone:

##

### 1. Access the Voice Cloning Feature

Navigate to the [Play AI App](https://play.ai/home) and log in to your account. Once logged in, locate and click on the **Create Voice Clone** option in the left navigation bar.

<img className="rounded-2xl" src="https://mintcdn.com/playhtinc/oLfqv-LO9FzqCeTi/media/voice-cloning/img/createVoiceCloneButton.png?fit=max&auto=format&n=oLfqv-LO9FzqCeTi&q=85&s=0df4d21d47560c14ba3b196efd5cc46a" alt="Create Voice Clone button in navigation" width="305" height="82" data-path="media/voice-cloning/img/createVoiceCloneButton.png" />

### 2. Choose Your Cloning Method

When the modal appears, you'll see two options:

<Note>Minimum 30 sec of audio is required for Instant Cloning</Note>

<CardGroup cols={2}>
  <Card title="Instant Clone" icon="bolt">
    <ul>
      <li>**For Quick cloning of your voice**</li>
      <li>- Requires only 30 seconds of audio</li>
      <li>- Results available instantly</li>
      <li>- Record your voice on the fly</li>
      <li>- Upload an existing audio file</li>
    </ul>

    <ul />
  </Card>

  <Card title="High Fidelity Clone" icon="sparkles" className="hover:bg-gray-50 dark:hover:bg-gray-800 transition-colors duration-200">
    <ul>
      <li>**For professional results**</li>
      <li>- Requires 20+ minutes of audio</li>
      <li>- Captures nuanced speech patterns</li>
      <li>- Preserves authentic accents</li>
      <li>- Superior voice quality</li>
      <li>- Takes longer time to train</li>
      <li>- Recommended for commercial use</li>
    </ul>
  </Card>
</CardGroup>

### 3. Provide Your Audio Sample

#### For Instant Cloning:

<Note>The **Voice Gender** setting for Instant Clones currently does not have any effect!</Note>

* **Recording Option**: Click the record button and speak naturally for at least 30 seconds
  <img className="rounded-2xl" src="https://mintcdn.com/playhtinc/oLfqv-LO9FzqCeTi/media/voice-cloning/img/recordVoiceButton.png?fit=max&auto=format&n=oLfqv-LO9FzqCeTi&q=85&s=33abfb53891cbe1f867b00afffcd9afc" alt="Create Voice Clone button in navigation" width="761" height="107" data-path="media/voice-cloning/img/recordVoiceButton.png" />
* **Upload Option**: Upload a pre-recorded audio file (minimum 30 seconds)
  <img className="rounded-2xl" src="https://mintcdn.com/playhtinc/oLfqv-LO9FzqCeTi/media/voice-cloning/img/uploadAudioButton.png?fit=max&auto=format&n=oLfqv-LO9FzqCeTi&q=85&s=69757b45ffdeeedaece15ef5cca06581" alt="Create Voice Clone button in navigation" width="759" height="174" data-path="media/voice-cloning/img/uploadAudioButton.png" />

#### For High Fidelity Cloning:

* Upload one or more audio files totaling **up-to 30 minutes** (do not exceed)
* Ensure consistent audio quality throughout
* Use clear recordings without background noise

<Tip>
  **Best Practices for Audio Samples:**

  <ul>
    <li>Use a high-quality microphone</li>
    <li>Higher audio quality shall yield better results</li>
    <li>Record in a quiet environment</li>
    <li>Speak naturally and be clear</li>
    <li>Include different speaking styles (questions, statements, emotions)</li>
  </ul>
</Tip>

<Accordion title="High Fidelity Fine-tune parameters" defaultOpen={false}>
  <Warning>
    It is recommended that you **do not change these.** Changing them might cause instability in output.
  </Warning>

  Available parameters for High Fidelity Voice Cloning:

  <img className="rounded-2xl" src="https://mintcdn.com/playhtinc/oLfqv-LO9FzqCeTi/media/voice-cloning/img/fineTuneParams.png?fit=max&auto=format&n=oLfqv-LO9FzqCeTi&q=85&s=ef2819cf1a035e5f1839e64cd77568a0" alt="Create Voice Clone button in navigation" width="765" height="609" data-path="media/voice-cloning/img/fineTuneParams.png" />

  <ul>
    <li>
      <strong>Maximum Iteration to Train:</strong> Controls the total duration of model training. Higher values mean
      longer training time but potentially better results.
    </li>

    <li>
      <strong>Number of iterations to warm up:</strong> Initial training phase where the model gradually adjusts its
      parameters before full training begins. Helps establish a stable starting point.
    </li>

    <li>
      <strong>Learning Rate:</strong> Determines how much the model's weights are adjusted in each training iteration.
      Higher values mean faster learning but risk instability.
    </li>

    <li>
      <strong>Rank:</strong> Controls how much the model can be modified by the input voice. Higher values allow more voice
      influence but should be used cautiously to avoid overfitting.
    </li>

    <li>
      <strong>Number of Vocoder Epochs:</strong> Specifies how many times the vocoder (audio synthesis component) goes
      through the training data. More epochs can improve audio quality but increase training time.
    </li>
  </ul>
</Accordion>

### 4. Process Your Voice Clone

After submitting your audio:

* **Instant clones** typically process within \~1 minute
* **High Fidelity clones** may take longer depending on audio length (\~35 mins)
* You'll receive a notification when your clone is ready

### 5. Access Your Cloned Voices

Once processing is complete, navigate to [Your Cloned Voices](https://play.ai/voices/voice-clones) to:

* Preview your cloned voice
* Test with different text inputs
* Manage voice settings
* Use in your projects

<Tip>
  {' '}

  Learn how to get the voice ID here: [Get ID for a voice](/documentation/text-to-speech/tts-voices#voice-library)
</Tip>