> For the complete documentation index, see [llms.txt](https://docs.bottalk.io/docs/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.bottalk.io/docs/elevenlabs-guides/multiple-voices-in-bottalk-articles.md).

# Multiple Voices in BotTalk Articles

This guide explains how to integrate and control multiple voices from elevenlabs in your BotTalk articles using SSML voice tags. The functionality is particularly useful for creating more dynamic, int

***

### Step 1: Activate SSML Tag Support in Audio Rules

To begin using different voices, you must first enable SSML tags in your BotTalk project settings.

1. Go to your **Test Project**.
2. Navigate to **Audio Rules**.
3. Enable the option that allows SSML when the article label is set to `"interview"`.

📸 *Refer to the image below for the correct setting toggle.*

<figure><img src="https://2378192786-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FirnDC5K5ndnjPJHyDBre%2Fuploads%2FADUcfycorx0rE8ka4O5E%2Fimage(3).png?alt=media&amp;token=6761abf4-f433-4267-a9d4-1daa0344b69e" alt=""><figcaption></figcaption></figure>

***

### Step 2: Label the Article

To activate SSML usage in a specific article:

1. Open the article in the BotTalk editor.
2. Add the label **`interview`**.

This tells the system to interpret SSML tags, including `<voice>`, in the article content.

📸 *See the image below on where to add the label.*

<figure><img src="https://2378192786-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FirnDC5K5ndnjPJHyDBre%2Fuploads%2FFT8tRR5f9wm8SMCFX2wG%2Fimage(4).png?alt=media&amp;token=52d8faf4-adbd-4871-8e56-4d015b379d33" alt=""><figcaption></figcaption></figure>

{% hint style="info" %}
Of course you can use [our API](/docs/help/endpoints.md#articles) to give labels programmatically.&#x20;
{% endhint %}

***

### Step 3: Insert SSML Voice Tags

With the article labeled and SSML enabled, you can now add voice-specific tags within your article content:

```xml
<voice name="de-DE-MatildaXI" vol="-10">
  This is the voice number one
</voice>

<voice name="de-DE-RobXI" vol="40">
  And this is the voice number two
</voice>

```

Each `<voice>` tag allows you to:

* **Specify a voice** using the `name` attribute.
* **Adjust volume** using the optional `vol` attribute, which accepts numerical values (positive = louder, negative = softer).

💡 *Different voices may have different natural volumes, so the `vol` attribute helps balance audio levels for a smoother listening experience. You can also set* [*an audio rule determining volume boost for a specific voice*](/docs/text-to-speech/automation-rules.md#volume-boost)*.*

***

### Tips

* Always test your output to ensure voice transitions sound natural.
* Use volume adjustments conservatively to avoid clipping or overly quiet segments.
* Combine with pauses or prosody tags for advanced speech tuning.