ElevenLabs Text to Speech

Converts a text input into an audio file using the ElevenLabs text-to-speech service and saves it to the workflow's working folder.

Purpose

Use this task when a workflow needs to produce spoken audio from text, such as generating voice announcements, narration for reports, or audio notifications. The task provides control over which voice is used and how the voice sounds through stability and similarity settings. The resulting audio file can be referenced by downstream tasks for distribution or further processing.

Inputs

Field	Type	Required	Description
Input Text	Multi-line Text	No	The text to convert to speech.
Voice	Dropdown	Yes	The voice to use for synthesis. Options: Rachel, Drew, Clyde, Paul, Aria, Domi, Sarah.
Stability	Text	No	A value from 0 to 1 controlling how consistent the voice sounds across repeated generations. Higher values produce a more stable, less expressive delivery. Defaults to 0.75.
Similarity Boost	Text	No	A value from 0 to 1 controlling how closely the output matches the selected voice's characteristics. Defaults to 0.75.
Output File Name	Text	No	The file name for the saved audio file, including extension (e.g. output.mp3). Defaults to output.mp3.

Outputs

Name	Description
AudioFilePath	The full path to the generated audio file saved in the workflow's working folder. Downstream tasks can use this path to attach, send, or further process the file.