Google Text-to-Speech

Convert text or SSML markup into a spoken audio file using the Google Cloud Text-to-Speech service.

Purpose

Use this task when a workflow needs to produce audio output from dynamically generated or static text. It supports multiple voices, languages, and audio formats, making it suitable for narration, voice alerts, or audio message generation. The task splits long inputs into manageable chunks and combines them into a single output file.

Inputs

Field	Type	Required	Description
ThirdParty - Google Cloud	Text	Yes	The name of the configured Google Cloud third-party credential to authenticate with the Text-to-Speech API.
Input Type	Dropdown	Yes	Whether the input is plain Text or SSML markup.
Text	Multi-line Text	Yes	The plain text content to synthesise into speech.
SSML	Multi-line Text	Yes	The SSML-formatted input for advanced speech control such as pauses and emphasis.
Voice	Text	Yes	The full Google Cloud voice name to use, for example en-US-Neural2-D.
Audio Format	Dropdown	Yes	The output audio format: MP3, OGG_OPUS, or LINEAR16 (WAV).
Speaking Rate	Text	No	Playback speed multiplier. Defaults to 1.0 (normal speed).
Pitch (st)	Text	No	Pitch adjustment in semitones. Defaults to 0.0.
Volume Gain (dB)	Text	No	Volume adjustment in decibels. Defaults to 0.0.
Sample Rate (Hz)	Text	No	Sample rate override in hertz, for example 24000 or 48000. Required when Audio Format is LINEAR16.
Chunk Size (chars)	Text	No	Maximum characters per synthesis request. Defaults to 4500.
File Name	Text	Yes	Base name for the output audio file, without extension.

Visibility Rules

Text is only shown when Input Type is set to Text.

SSML is only shown when Input Type is set to SSML.

Outputs

Name	Description
Audio	An object containing the full output file path (Audio.File), the voice used (Audio.Voice), the audio format (Audio.Format), the number of chunks processed (Audio.Chunks), and the total character count (Audio.Characters).