Skip to main content

Text to Speech Streaming Node

The Text to Speech Streaming Node converts text input into streaming audio using various AI-powered text-to-speech models. Unlike the standard Text to Speech node, this node streams audio in real-time, providing immediate playback as the audio is generated, which is ideal for longer content and improved user experience.

Text to Speech Streaming node

Basic Usage​

Use the Text, Text Input, Text to Speech Streaming node for your process.

Inputs​

The Text to Speech Streaming node accepts the following input:

  • Input: The text content to be converted into streaming speech audio.

Outputs​

The Text to Speech Streaming node automatically plays the audio as it streams, without requiring a separate output connection.

Configuration​

Voice Model Selection​

Select the AI voice model to use for speech synthesis:

  • OpenAI Alloy: Neutral and balanced voice suitable for general-purpose applications
  • OpenAI Echo: Clear and articulate voice ideal for educational content
  • OpenAI Fable: Warm and expressive voice perfect for storytelling
  • OpenAI Onyx: Deep and authoritative voice for professional content
  • OpenAI Nova: Energetic and engaging voice for dynamic presentations
  • OpenAI Shimmer: Soft and gentle voice suitable for calm narration
  • Other supported models: Additional voice models available in your LearningFlow instance

Select Play Sound Size​

Choose the audio player size for the streaming playback:

  • Small: Compact player suitable for minimal interface space
  • Medium: Standard player size with balanced visibility and functionality

Usage​

Setting Up Text to Speech Streaming​

  1. Add the node to your flow canvas.
  2. Select Voice Model: Choose the AI voice model that best fits your content and audience.
  3. Select Play Sound Size: Choose Small or Medium based on your interface requirements.
  4. Connect Input: Link from upstream nodes (e.g., Text Input, Form Node, Display Text, AI General Prompt) to provide the text content.

Example Workflows​

Story Narration​

Scenario: Create a streaming story reader that narrates text content in real-time with immediate audio playback.

Text to Speech Streaming Example

Steps to Create the Flow:

  1. Add a Start Node.

  2. Add and connect a Text node with your story content.

    • Example for Text:
    The rain hammered against the rooftop as Alex tightened their grip on the old, tattered
    journal. Each page held the...

  3. Add and connect a Text to Speech Streaming Node.

    • Select Voice Model: OpenAI Alloy
    • Select Play Sound Size: Small
    • Connect the Text node's Output to the Text to Speech Streaming's Input

Result: The story text is immediately narrated with streaming audio, providing real-time playback as the audio is generated.