Skip to main content
Generate Speech turns text into spoken audio using a speech synthesis model. This node runs on a selectable model and consumes credits when it runs.

When to use

  • Voiceovers
  • Narration
  • Audio ads

Inputs

text
required
The text to speak. Required. Supports loop mode.
Inline prompt. You don’t need a separate Text Prompt node for fixed text — type it directly on the node. The inline field appears whenever the text input is unconnected and disappears once you wire a text input in. Connect a Text Prompt node only when you want to drive the text from upstream or expose it as an app input. Type @ to mention a connected input by name — text inputs insert their content into the text, media inputs insert their name.

Outputs

audio
The generated speech.

Configuration

string
default:""
The voice to use for synthesis.
string
default:"en"
Language code for the spoken output.
number
default:0.5
Voice stability, from 0 to 1. Higher values produce a more consistent delivery.
number
default:0.75
How closely the output matches the chosen voice, from 0 to 1.
number
default:0
Style exaggeration, from 0 to 1.
number
default:1
Playback speed, from 0.5 to 2.
This node runs on a selectable model. See Audio models for supported models and Model settings for available options.