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

# Voices

> Browse the Aivah voice library and clone your own voice

# Voices

The **Voices** page (`Side nav → Customization → Voices`, or `/avatars/voices`) lists every voice your account can use – both Aivah's built-in library and the private voice clones you upload.

Voices are the speech engine for:

* The chat composer (Playground)
* The avatar in [Avatar chat](/interaction-hub/voice)
* Telephony calls (see [Twilio Phone Setup](/integration/twilio-phone-setup))
* Channel responses where audio is supported

## What you see

* A grid of voice cards. Each card includes:
  * Voice name
  * Provider / model family (so you know which LLMs it pairs with)
  * Playback controls to preview the voice
  * A *Set as default* action
* A **Create** button (top-right) for adding a new voice clone.
* Search and pagination across the full library.

<Frame caption="Voices page – built-in voices plus your private clones, each with playback and provider badge">
  <img src="https://mintcdn.com/opinionai/tR4nAAll3jemMkvA/images/voices-list.png?fit=max&auto=format&n=tR4nAAll3jemMkvA&q=85&s=08cc8c5c564225ded338e4c1ced12ecf" alt="Voices list" width="4112" height="2658" data-path="images/voices-list.png" />
</Frame>

<Tip>
  Switching the LLM provider in the chat composer may filter the available voice list. For example, Gemini voices appear when a Gemini model is active, and OpenAI Realtime voices appear when an OpenAI Realtime model is active.
</Tip>

## Clone a voice

<Steps>
  <Step title="Click Create">
    Press **+ Create** in the header. The **Add voice** dialog opens.

    <Frame caption="Add voice modal – Name, Language, Voice Sample, and Description">
      <img src="https://mintcdn.com/opinionai/tR4nAAll3jemMkvA/images/voice-clone-modal.png?fit=max&auto=format&n=tR4nAAll3jemMkvA&q=85&s=fb22673edd8a3a9827f471838fdfae7e" alt="Add voice modal" width="4112" height="2658" data-path="images/voice-clone-modal.png" />
    </Frame>
  </Step>

  <Step title="Pick the language">
    Select the language the voice will primarily speak (English, French, German, Spanish, Portuguese, etc.).

    <Frame caption="Language picker in the Add voice modal">
      <img src="https://mintcdn.com/opinionai/tR4nAAll3jemMkvA/images/voice-clone-language-picker.png?fit=max&auto=format&n=tR4nAAll3jemMkvA&q=85&s=88fdd04515e7d39f8a16f90f064c5864" alt="Voice clone language picker" width="4112" height="2658" data-path="images/voice-clone-language-picker.png" />
    </Frame>
  </Step>

  <Step title="Upload a clean reference recording – or record one">
    You can either **Upload File** (a short, mono audio file up to 10 MB) or **Record Audio** directly in the browser (up to 1 minute). For best results:

    * Keep the recording free of background noise, music, or other voices
    * Aim for natural pacing – read a short paragraph rather than a single sentence
    * Use a quality microphone and the highest-fidelity export available

    <Frame caption="Record Audio mode – capture up to 1 minute right in the browser">
      <img src="https://mintcdn.com/opinionai/tR4nAAll3jemMkvA/images/voice-clone-record-audio.png?fit=max&auto=format&n=tR4nAAll3jemMkvA&q=85&s=a83b0892416c6aa89b6bf09f09a45c57" alt="Voice clone record audio" width="4112" height="2658" data-path="images/voice-clone-record-audio.png" />
    </Frame>
  </Step>

  <Step title="Name and describe the voice">
    Give the voice a short, descriptive name (for example *Sarah – Casual*) and add a description of the voice characteristics. This is what appears in pickers throughout Aivah.
  </Step>

  <Step title="Add to my voice">
    Click **Add to my voice**. The new voice enters processing. Once processed, it shows up in the list and can be selected wherever a voice can be picked.
  </Step>
</Steps>

## Use a voice

Voices can be selected in three places:

1. **Chat composer pills** – the voice pill in **New chat** or in the configuration pop-over for an existing conversation.
2. **Preferences modal** (palette icon in Avatar chat) – set the voice your avatar speaks with.
3. **Integration configuration** – Telephony and Channels both expose a voice picker so calls or channel messages use the right voice.

## Default voice

Mark a voice as your default to pre-fill the picker every time you start a new conversation. You can change the default at any time from the Voices page.

## Best practices

* **Cleanly trim recordings** – background noise during the training clip is reproduced in the clone.
* **Match accent and language** – clone voices reproduce the linguistic patterns of the source.
* **Test before publishing** – preview the clone in the Playground before assigning it to a shared agent or a phone number.
* **Pair voice and LLM** – some voice families are only available with specific LLM providers; if a voice disappears, switch the LLM back to the matching family.

## Related guides

* [Customization overview](/avatars/overview)
* [Hub Talk Mode and Avatar chat](/interaction-hub/voice)
* [Twilio Phone Setup](/integration/twilio-phone-setup)
* [Voice-Only Agents](/share/voice-only-agents)