Voice Prompt Node

The Voice Prompt node converts text to speech and plays it to the caller during a voice conversation. It supports SSML markup for fine-grained control over pronunciation, voice selection from multiple providers, and barge-in to allow the caller to interrupt.

When to Use

• You need to speak a message to the caller in a voice bot flow.
• You want fine-grained control over speech output (rate, pitch, SSML).
• You need to allow the caller to interrupt the prompt (barge-in).
• You want to use a specific TTS voice or provider for certain prompts.

Configuration

Property	Description	Default
Prompt Text	The text to speak. Supports {{variable}} interpolation.	Empty (required)
Enable SSML	Enable SSML markup in the prompt text for advanced speech control.	false
TTS Integration	Optional override for the TTS integration. Leave empty to use the tenant default.	Empty
Voice Name	Select a specific voice for this prompt. Available voices include en-US Wavenet A-D, en-GB Wavenet A-B, and es-ES Wavenet B-C.	Default Voice

Advanced Settings

Property	Description	Default
Speaking Rate	Speech speed multiplier (0.25 to 4.0). Values below 1.0 slow down speech; above 1.0 speed it up.	1.0
Pitch	Voice pitch adjustment (-20 to +20 semitones).	0
Allow Barge-in	Allow the caller to interrupt the prompt by speaking.	false
Timeout	How long to wait after speaking before continuing (0 to 30,000 ms).	5000
Barge-in Output Variable	When barge-in is enabled, the variable to store the caller's interruption text.	Empty

SSML Support

When SSML is enabled, you can use markup to control pronunciation:

<speak>
  Your order <say-as interpret-as="digits">12345</say-as> has shipped.
  <break time="500ms"/>
  Expected delivery is <say-as interpret-as="date" format="mdy">02/28/2026</say-as>.
</speak>

imageVoice Prompt node config panel showing prompt text area with SSML markup, Enable SSML toggle turned on, TTS integration selector, voice name dropdown, speaking rate slider, pitch adjustment, and allow barge-in toggle

Voice Prompt configuration with SSML toggle

Channel Behavior

Channel	Behavior
Voice	Text is converted to speech via TTS and played to the caller
Web / SMS / WhatsApp	The prompt text is sent as a regular text message (TTS is skipped)

Handles

Handle	Direction	Description
Input	In	Receives execution from the previous node
Output	Out	Continues to the next node after the prompt finishes playing

TIP

Use barge-in for long prompts (like menu options) so callers who already know what they want can skip ahead. Store the barge-in text in a variable and process it downstream.