WorqHat
AI Nodes

Text To Speech

Category
AI
Node Type
Audio Processing

Overview

The Text to Speech Node converts written text into natural-sounding speech using advanced AI voice models powered by ElevenLabs. 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 you to bring your own custom voice IDs from ElevenLabs for a personalized experience.

Description

Turn any text into human-like speech.

Use the Text to Speech Node to generate high-quality audio from text. Whether you need a standard narrator or a specific custom voice, this node handles it seamlessly.

Natural AI Voices

Choose from a library of high-quality, pre-configured AI voices.

Custom Voice Cloning

Use your own ElevenLabs Voice IDs to generate speech in a specific persona.

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.

textstringRequired
The text content to be converted into speech. You can use static text or dynamic variables from previous nodes.
Example
"Welcome to our service! How can I help you today?"
voiceIdstringRequired
The unique identifier of the voice used for speech synthesis. You can use one of the predefined voices or any valid **ElevenLabs Voice ID**.
Example
"TX3LPaxmHKxFdv7VOQHJ" (Liam) or "Your_Custom_Voice_ID"
Available Voices

You can use any valid voice ID from ElevenLabs. Here are some popular presets:

  • "SOYHLrjzK2X1ezoPC6cr" – Harry
  • "TX3LPaxmHKxFdv7VOQHJ" – Liam
  • "ThT5KcBeYPX3keUQqHPh" – Dorothy
  • "XB0fDUnXU5powFXDhCwa" – Charlotte

Output Parameters

After execution, the Text to Speech node returns information about the generated audio and process details.

audiostringOptional
The file reference or URL of the generated audio output. This is the main result used in downstream nodes.
Example
"https://example.com/audio/generated_speech.mp3"
processingCountnumberOptional
Indicates the total number of audio segments generated.
Example
1
processingTimestringOptional
The total time taken to generate the speech output.
Example
"2025-10-28T13:20:45.123Z"
processingIdstringOptional
A unique identifier assigned to this specific speech generation request.
Example
"tts-90128xkf"
messagestringOptional
A status message indicating the result of the operation.
Example
"Speech generated successfully."
Accessing Data

Access the generated audio URL in your workflow using:

{{nodeId.output.audio}}

Output Type

Output 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

Generate speech using a predefined voice.

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

Example 2: Dynamic Content with Custom Voice

Use a variable for text and a custom ElevenLabs Voice ID.

{  "text": "{{textGeneration.output.summary}}",  "voiceId": "21m00Tcm4TlvDq8ikWAM"}
{  "processingCount": 1,  "processingTime": "2025-10-28T14:05:09.004Z",  "processingId": "tts-90782pqr",  "audio": "https://example.com/audio/summary_rachel.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

Enter a predefined voice ID (e.g., for "Liam") or paste your own ElevenLabs Voice ID.

4

Run the Workflow

Execute the workflow to automatically convert the text into an audio file.

5

Use Output

Use the generated audio URL in downstream nodes like Slack, Email, or File Storage.

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.

Do / Don’t

Do
  • ✔️ Use punctuation in your text to control pacing and intonation.
  • ✔️ Test different voices to find the one that best matches your brand or context.
  • ✔️ Use custom ElevenLabs Voice IDs for unique character voices.
Don’t
  • ❌ Don’t send extremely long blocks of text without breaks; split them if necessary.
  • ❌ Don’t use invalid or expired Voice IDs.
  • ❌ Don’t expect the AI to perfectly pronounce complex technical jargon without phonetic spelling.

Common Errors

Missing text inputErrorOptional
The text field was left empty or not connected. Provide valid text directly or connect to a previous node.
Invalid voiceIdErrorOptional
An unsupported or incorrect voiceId was entered. Use a supported ID or a valid ElevenLabs Voice ID.
Audio generation failedErrorOptional
The AI model encountered an error or timed out. Retry after a short delay or shorten the text.
Empty audio outputErrorOptional
The node did not connect correctly to downstream components. Recheck connections.

Example Workflow Integration

Use Case 1: Daily Motivational Quotes

Generate a daily quote and convert it to audio for a morning briefing.

  1. Trigger Node: REST API (receives request).
  2. AI Node: Text Generation (generates a quote).
  3. Text to Speech Node: Converts the quote to audio using "Harry".
  4. Slack Node: Posts the audio file to a channel.

Workflow Data Flow:

{{textGeneration.output.quote}}     →  {{textToSpeech.input.text}}
{{textToSpeech.output.audio}}       →  {{slack.input.fileUrl}}

Use Case 2: Automated Customer Support Response

Generate a personalized audio response for a customer query.

  1. Text Generation Node: Generates a helpful response to a user question.
  2. Text to Speech Node: Converts the response to speech using a custom brand voice.
  3. Return State Node: Returns the audio URL to the frontend application.

Workflow Data Flow:

{{aiResponse.output.text}}          →  {{textToSpeech.input.text}}
"My_Brand_Voice_ID"                 →  {{textToSpeech.input.voiceId}}