# Voice Remix

> Describe a voice in plain words and hear it speak your preview text. The quick way to explore voice ideas, with no reference recording and no settings to tune.

Source: https://nodaro.ai/docs/nodes/audio/voice-remix

The **Voice Remix** node creates a voice from a description in plain words and lets you hear it speak a preview text. It is the quick way to explore voice ideas: you need no reference recording and no settings. For a voice you can refine, reproduce and keep, use [Voice Design](https://nodaro.ai/docs/nodes/audio/voice-design).

- Found in: Audio › Voices
- Output: audio
- API type: `voice-remix`

## When to use it
- Try several voice styles for a project before you choose one.
- Hear a character voice from a written description.
- Make voice samples for a client to approve before production.
- Brainstorm narrator styles for an audiobook or a video.

## Quick start
### Add the node

Press Tab on the canvas and choose **Audio › Voices › Voice Remix**.

### Describe the voice

Open the settings panel and write the **Voice Description**, for example: "A warm, deep male voice with a slight British accent and a calm delivery."

### Write the preview text

Under **Preview Text**, write a sentence or two for the voice to speak.

### Run it

Click **Run** on the node, and listen to the preview on the node.

Workflow: Two voice pickers add their wording to the description, and Voice Remix returns a preview of the voice.

- Voice Character → Voice Remix (audio style)
- Voice Delivery → Voice Remix (audio style)

## Inputs and output
| Input | Accepts | What it does |
| --- | --- | --- |
| **Audio style** | Voice pickers, such as Voice Character and Voice Delivery | The settings panel lists the connected pickers and shows the final voice description with their wording. |

The output, **Audio**, is the audio preview: the new voice speaking your preview text.

## Settings
| Setting | What it does |
| --- | --- |
| **Voice Description** | The voice in plain words: age, gender, accent, tone, pace and emotion. |
| **Preview Text** | The text the new voice speaks in the preview. A run needs a preview text. |
| **Pre & post text** | Text that is always added before and after the description. It is hidden from people who use your workflow as an app. See [Prompt pre and post text](https://nodaro.ai/docs/concepts/prompt-pre-post-text). |

## Tips
- **Be specific.** Include age range, gender, accent, tone, pace and emotional quality. Small wording changes can give clearly different voices.
- **Use realistic preview text.** A sentence or two of natural speech shows the voice better than single words.
- **Run it more than once.** Each run can give a slightly different voice, even with the same description.
- **Move to Voice Design to keep a voice.** Voice Remix returns a preview only. [Voice Design](https://nodaro.ai/docs/nodes/audio/voice-design) returns a voice ID and lets you fix a seed.
- **Apply the voice to a recording.** When you have found a voice style you like, use [Voice Changer](https://nodaro.ai/docs/nodes/audio/voice-changer) to put a matching voice on an existing recording.

## From the API
`POST /v1/voice-remix` takes `text` (the preview text) and `voiceDescription`. The MCP tool is `voice_remix`. See [Voice and media](https://nodaro.ai/docs/developers/api/voice-and-media).

## Frequently asked questions

### What does Voice Remix do?

It creates a voice from a written description and returns an audio preview of that voice speaking your preview text. You need no reference recording.

### Does Voice Remix give me a voice I can reuse?

No. Voice Remix returns an audio preview only. For a voice with a voice ID and a seed you can reproduce, use the Voice Design node.

### Why does the same description give a different voice each time?

Each run generates a new voice, so results can differ slightly even with the same description. Run it a few times and keep the preview you like, or move to Voice Design and fix a seed.

### How do I write a good voice description?

Name concrete qualities such as age range, gender, accent, tone, pace and emotion. "Gravelly baritone, speaks slowly, sounds like a late-night radio host" works better than "a cool voice".