> ## Documentation Index
> Fetch the complete documentation index at: https://docs.imagine.art/llms.txt
> Use this file to discover all available pages before exploring further.

# Generate Voice

## Summary

The Voice Node converts text into natural-sounding speech using AI text-to-speech models. Write or connect a prompt, select a voice, and the node generates an audio output that sounds like a real person speaking. Use it for voiceovers, narration, dialogue, or any workflow that needs spoken audio from text.

## How to Use

<Steps>
  <Step title="Add the Node">
    Click the Add (+) button and select Voice from the Audio node category.
  </Step>

  <Step title="Write Your Text">
    Type what you want spoken into the prompt field, or connect a Prompt or AI Copilot node.
  </Step>

  <Step title="Select a Voice">
    Choose a voice from the Voice dropdown (e.g., Roger). Each voice has a distinct tone, pitch, and character.
  </Step>

  <Step title="Run">
    Click Run, and the AI generates an audio file of the selected voice speaking your text.
  </Step>
</Steps>

## Choosing the Right Settings

| Setting          | Type                   | Impact on Output                                                                                                  |
| ---------------- | ---------------------- | ----------------------------------------------------------------------------------------------------------------- |
| Voice            | Dropdown (e.g., Roger) | Selects the voice character used for speech generation. Different voices vary in tone, gender, accent, and style. |
| Prompt           | Text Input             | The text content that will be converted into speech.                                                              |
| Stability        | Slider (0–100%)        | Controls how consistent the voice sounds across the output.                                                       |
| Similarity Boost | Slider (0–100%)        | Controls how closely the output matches the selected voice.                                                       |
| Speed            | Slider                 | Adjusts the speaking pace of the generated audio.                                                                 |
| Timestamps       | Checkbox               | When enabled, returns word-level or sentence-level timestamps alongside the audio output.                         |

## Sample Use Cases

<AccordionGroup>
  <Accordion title="Voiceovers for AI-Generated Videos" defaultOpen>
    Generate a voiceover and connect it to a Combine Audio & Video node to add narration to any video in your workflow.
  </Accordion>

  <Accordion title="Multilingual Audio Content" defaultOpen>
    Write the same script in multiple languages and generate a voice for each — perfect for localizing video content without hiring voice actors.
  </Accordion>

  <Accordion title="Podcast and Audio Previews" defaultOpen>
    Quickly generate audio previews of scripts, blog posts, or ad copy to hear how they sound before recording with a real voice.
  </Accordion>
</AccordionGroup>