Skip to main content
Category: AI Type: Audio Processing

​
Overview

The Text to Speech Node converts written text into natural-sounding speech using advanced AI voice models. It allows you to transform text-based content (like messages, summaries, or prompts) into an audio format that can be played, downloaded, or passed to other workflow nodes for further use. This node is designed for no-code workflows, meaning you can generate spoken audio directly from text without any programming. It supports multiple pre-configured voices and allows integration with other nodes for automated voice responses or multimedia content creation.

​
Description

Use the Text to Speech Node to turn any text into human-like speech. Simply provide the text you want to convert and choose a voice from the available options. The node outputs an audio file (or URL) that contains the generated voice output, which can then be used in downstream nodes like playback, file storage, or notifications.

​
Input Parameters

The Text to Speech node accepts flat key-value inputs that define what text to convert and which voice to use.
  • text The text content to be converted into speech. You can use static text or dynamic variables from previous nodes, for example: 
    {{nodeId.output.field}}
  • voiceId The unique identifier of the voice used for speech synthesis. Available voices include:
    • "SOYHLrjzK2X1ezoPC6cr" – Harry
    • "TX3LPaxmHKxFdv7VOQHJ" – Liam
    • "ThT5KcBeYPX3keUQqHPh" – Dorothy
    • "XB0fDUnXU5powFXDhCwa" – Charlotte
Instructions: Provide all input parameters as flat key-value pairs. You can reference data dynamically within the workflow using: 
{{nodeId.input.<key>}}
or 
{{nodeId.output.<key>}}

​
Output Parameters

After execution, the Text to Speech node returns information about the generated audio and process details.
  • processingCount Indicates the total number of audio segments or speech outputs generated.
  • processingTime The total time taken to process and generate the speech output, returned in ISO timestamp format.
  • processingId A unique identifier assigned to this specific speech generation request. Useful for tracking or debugging individual runs.
  • audio The file reference or URL of the generated audio output. This can be used in downstream nodes to send, play, or store the generated speech.
  • message A short status message indicating whether the operation was successful or if an error occurred.

​
Output Type

Type: audio This node always outputs an audio file or reference. Do not modify this value — it ensures proper audio handling in your workflow.

​
Example Usage

​
Example 1 — Simple Text to Speech

Input: 
{
  "text": "Welcome to the workflow automation demo!",
  "voiceId": "TX3LPaxmHKxFdv7VOQHJ"
}
Output: 
{
  "processingTime": "2025-10-28T13:20:45.123Z",
  "processingId": "tts-90128xkf",
  "audio": "https://example.com/audio/welcome_demo.mp3",
  "message": "Speech generated successfully."
}

​
Example 2 — Using Variables from Another Node

Input: 
{
  "text": "{{rest-api-trigger-initial.input.test_input}}",
  "voiceId": "ThT5KcBeYPX3keUQqHPh"
}
Output: 
{
  "processingCount": 1,
  "processingTime": "2025-10-28T14:05:09.004Z",
  "processingId": "tts-90782pqr",
  "audio": "https://example.com/audio/demo.mp3",
  "message": "Text processed successfully."
}

​
How to Use in a No-Code Workflow

  1. Add the Node: Drag and drop the Text to Speech Node into your workflow editor.
  2. Connect Input: Link the output of a text-generating node (like Text Generation) or static text as the input for the text field.
  3. Select a Voice: Choose a voice ID (e.g., “Harry” or “Charlotte”) for speech output.
  4. Run the Workflow: Execute the workflow to automatically convert the text into an audio file.
  5. Access Audio Output: The generated file link can be used in:
    • Notification systems
    • Audio playback modules
    • File storage or sharing nodes

​
Best Practices

  • Keep text under 2,000 characters per request for faster processing.
  • Choose a consistent voice ID across similar nodes for a uniform tone.
  • Use descriptive variable names like {{introNode.output.text}} to make the workflow readable.
  • For multilingual support, verify that your chosen voice supports the target language.

​
Example Workflow Integration

Scenario: A workflow where AI generates daily motivational quotes and automatically converts them to audio. Example Flow:
  1. Trigger Node: REST API (to receive input data)
  2. AI Node: Text to Speech (to convert text to speech)
  3. Process Node: Return State Node (to display the url containing the audio)

​
Common Errors

Below are common issues you might encounter while using the Text to Speech node, along with their causes and recommended solutions.
  • “Missing text input” Cause: The text field was left empty or not connected. Solution: Provide valid text directly or connect the text field to a previous node’s output.
  • “Invalid voiceId” Cause: An unsupported or incorrect voiceId was entered. Solution: Use one of the supported voice IDs listed in the input parameters or a verified custom voice ID.
  • “Audio generation failed” Cause: The AI model encountered an internal error or the request timed out. Solution: Retry after a short delay or reduce the length of the input text.
  • “Empty audio output” Cause: The node did not connect correctly to downstream workflow components. Solution: Recheck node connections and run the workflow again to ensure proper linkage.