Text to Dialogue

Generate multi-speaker dialogue audio where each line is spoken by a different voice.

Overview

The Text to Dialogue node uses ElevenLabs Dialogue V3 to produce a single audio file containing multiple speakers. Each line of dialogue is assigned a different voice, and the output is a cohesive conversational audio track. This is ideal for creating conversations, interviews, or any scenario requiring distinct speakers without manually generating and stitching individual TTS clips.

Configuration

Field Type Default Description
Dialogue Lines DialogueLine[] [{ text: "", voice: "Sarah" }] Array of dialogue entries, each with text content and a voice selection. Add or remove lines as needed
Stability number (select: 0, 0.5, 1.0) 0.5 Voice consistency across the dialogue. 0 = most expressive, 1.0 = most consistent
Language string "" (auto-detect) Target language code, or empty for automatic detection. Uses the full language list (ALL_LANGUAGES)

DialogueLine Fields

Field Type Description
id string Unique identifier for the line
text string The spoken text for this line
voice string Voice ID for this line’s speaker
voiceLabel string (optional) Display name of the selected voice

Inputs & Outputs

Common Use Cases

Tips