> For the complete documentation index, see [llms.txt](https://docs.myshell.ai/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.myshell.ai/ko/create/pro-config-mode/api-reference/widgets/7-bark-tts.md).

# Bark TTS

## Try it in the Widget Center

Click this [url](https://app.myshell.ai/robot-workshop/widget/1781991719128457216) to try this widget and copy the Pro Config template.

## Usage

#### Supported Languages

> * English
> * Chinese
> * German
> * Spanish
> * French
> * Hindi
> * Italian
> * Japanese
> * Korean
> * Polish
> * Portuguese
> * Russian
> * Turkish

The languages are auto-detected. Bark-TTS also supports serval non-speech sounds.

**Input Parameters**

<table><thead><tr><th>Name</th><th>Type</th><th>Description</th><th>Default</th><th data-type="checkbox">Required</th></tr></thead><tbody><tr><td>prompt</td><td><code>string</code></td><td><p>The text prompt for model to generate audio. Here are some non-speech sounds:</p><pre><code>                                    - [laughter]
                                    - [laughs]
                                    - [sighs]
                                    - [music]
                                    - [gasps]
                                    - [clears throat] 
                                    - — or ... |  for hesitations
                                    - ♪  | for song lyrics
                                    - Capitalization | for emphasis of a word
                                    - NARRATOR: / MAN: / WOMAN: | for bias towards speaker&#x3C;/td>&#x3C;td>Hello, my name is Suno. And, uh — and I like pizza. [laughs] But I also have other interests such as playing tic tac toe.&#x3C;/td>&#x3C;td>false&#x3C;/td>&#x3C;/tr>
</code></pre></td><td>Hello, my name is Suno. And, uh — and I like pizza. [laughs] But I also have other interests such as playing tic tac toe.</td><td>true</td></tr><tr><td>history_prompt</td><td><code>string</code></td><td><p>history choice for audio cloning, choose from the list. To mitigate misuse of this technology, we limit the audio history prompts to a limited set.</p><pre><code>                                    It is possible to use for example a german history prompt with english text. This usually leads to english audio with a german accent.&#x3C;/td>&#x3C;td>en_speaker_0&#x3C;/td>&#x3C;td>false&#x3C;/td>&#x3C;/tr>
</code></pre></td><td>en_speaker_0</td><td>true</td></tr><tr><td>text_temp</td><td><code>number</code></td><td>generation temperature during text encoding (1.0 more diverse, 0.0 more conservative)</td><td>0.7</td><td>false</td></tr><tr><td>waveform_temp</td><td><code>number</code></td><td>generation temperature during wavform generation (1.0 more diverse, 0.0 more conservative)</td><td>0.7</td><td>false</td></tr></tbody></table>

**Output Parameters**

| Name | Type     | Description                                                                                                              | File Type |
| ---- | -------- | ------------------------------------------------------------------------------------------------------------------------ | --------- |
| url  | `string` | The audio that was generated has been saved as an online URL. This link is temporary, so please save it for your own use | `audio`   |

**Output Example**

{% tabs %}
{% tab title="success" %}
{% code fullWidth="false" %}

```json
{
  "url": "https://cdn.myshell.ai/audio/chat/embed_obj/38145/20240423/fa7e6014529f41c1aa747f765f00c385.mp3"
}
```

{% endcode %}
{% endtab %}
{% endtabs %}