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.

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.

Of course you can use our API to give labels programmatically.

Step 3: Insert SSML Voice Tags

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

<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.

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.

PreviousElevenlabs GuidesNextDictionaries

Last updated