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

# Text-to-Speech

> Integrate AI text-to-speech capabilities into your product.

## What It Is

Text-to-speech is a built-in AI plugin that turns written text into natural-sounding speech. It adds voice output to apps you build — suitable for narration, read-aloud flows, accessibility, and voice interaction.

The plugin is enabled per project. Once enabled, the app generated by that project can use text-to-speech at runtime.

***

## Where to Find It

1. Open any project.
2. Switch to the **Build** tab.
3. Open **Skill Library** from the left navigation.
4. Find **Text-to-Speech** in the plugin cards.

The plugin is visible globally and supports Simplified Chinese, Traditional Chinese, Cantonese, English, Japanese, and Korean.

***

## Enable

Any of the following enables it — choose whichever you prefer:

* Hover the plugin card and click **Use**.
* Open the plugin detail page and click **Use** in the header.
* Confirm the plugin enablement card when the AI assistant suggests it in chat.

The AI assistant will guide the enablement process in the conversation. After it finishes, the plugin card shows a green enabled icon.

***

## Getting Started

1. Describe the read-aloud or narration feature in chat, or click **Use** on the plugin detail page.
2. superun automatically connects text-to-speech to your project.
3. Use generated speech in your product, then tune voices and playback behavior as needed.

Speech synthesis usage is billed based on actual consumption. Available voices, languages, and quotas depend on the current platform capabilities.

***

## Disable

Open the plugin detail page, click **Disable** in the header, and confirm in the dialog. You do not need to go through the chat flow.

***

## FAQ

<AccordionGroup>
  <Accordion title="Can I choose a voice or language?">
    Text-to-speech supports multiple voices and languages to cover common pronunciation needs. Available options depend on the current platform capabilities.
  </Accordion>

  <Accordion title="How is billing calculated?">
    Speech synthesis usage is billed based on actual consumption. Refer to the platform billing docs for the current pricing model.
  </Accordion>
</AccordionGroup>