Text to Speech

A guide to the Text-to-Speech action for converting written text into spoken audio.

The Text-to-Speech (TTS) Action converts written text into natural-sounding spoken audio. It uses advanced AI models to generate high-quality voiceovers, narrations, and audio clips directly from your text inputs.

This is ideal for:

• Creating audio versions of your blog posts or articles.

• Generating voiceovers for videos.

• Building accessibility features for users with visual impairments.

• Creating dynamic audio alerts and notifications.

How It Works

The action sends the input text to a sophisticated TTS model, which processes the text and synthesizes a human-like voice. You can choose from a variety of voices, languages, and accents to match your needs. The output is an audio file that can be saved or used in other workflow steps.

Configuration

Input Parameters

Parameter	Type	Description
Text	Text	The text you want to convert to speech. This can be static text or a variable from a previous action (e.g., {{llm_action.summary}}).
Voice	Select	Choose from a list of available AI-generated voices. Options range from male and female voices across different ages and accents.
Language	Select	The language of the input text (e.g., "English," "Spanish," "Japanese").

Output Parameters

Parameter	Type	Description
Output	File	The generated audio clip, typically in MP3 format.

Example: Creating an Audio Summary of a News Article

Let's say you have a workflow that scrapes a news article and uses an LLM to summarize it. Now, you want to create a short audio version of that summary.

1. Get the Summary: Your workflow has an LLM Action that outputs a text summary, available as the variable {{llm_action.summary}}.

2. Configure the Text-to-Speech Action:

   • Text: {{llm_action.summary}}

   • Voice: Select a clear, professional voice like "Alloy" or "Nova."

   • Language: "English"

3. Use the Audio:

   • The Output of the TTS action will be an MP3 file containing the spoken summary.

   • You can then connect this to a Save File Action to store the audio clip, or perhaps a Send Email Action to send the audio summary to a subscriber list.