> For the complete documentation index, see [llms.txt](https://help.imagine.art/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://help.imagine.art/workflows/audio-nodes/generate-voice.md).

# 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

1. Add the Node:
   * Click the Add (+) button and select Voice from the Audio node category.
2. Write Your Text:
   * Type what you want spoken into the prompt field, or connect a Prompt or AI Copilot node.
3. Select a Voice:
   * Choose a voice from the Voice dropdown (e.g., Roger). Each voice has a distinct tone, pitch, and character.
4. Run:
   * Click Run, and the AI generates an audio file of the selected voice speaking your text.

***

### 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

<details open>

<summary>Voiceovers for AI-Generated Videos</summary>

Generate a voiceover and connect it to a Combine Audio & Video node to add narration to any video in your workflow.

</details>

<details open>

<summary>Multilingual Audio Content</summary>

Write the same script in multiple languages and generate a voice for each — perfect for localizing video content without hiring voice actors.

</details>

<details open>

<summary>Podcast and Audio Previews</summary>

Quickly generate audio previews of scripts, blog posts, or ad copy to hear how they sound before recording with a real voice.

</details>

***

### Audio Models

Visit [Audio Models](https://help.imagine.art/workflows/ai-models/audio-models) to explore all available models and find the one that fits your audio needs.


---

# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.

## Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter, and the optional `goal` query parameter:

```
GET https://help.imagine.art/workflows/audio-nodes/generate-voice.md?ask=<question>&goal=<endgoal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is optional and describes the broader end goal you are ultimately trying to accomplish on behalf of the user. GitBook uses it to tailor the answer towards what is most useful for that goal.

The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.