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

# Make audio

> Turn a script into speech with a voice you choose.

The audio generator turns text into speech with the Eleven v4 model. Choose
**Audio** in Generate's sidebar to open it.

![The audio generator with the Eleven v4 model, the voice Adam, a short script, and the Delivery and Format settings above the Generate button.](https://mintcdn.com/zero-gen/m4I7fPs1rAXZSMjU/images/generate/audio-generator.png?fit=max\&auto=format\&n=m4I7fPs1rAXZSMjU\&q=85\&s=6c15105374a8f9bd9ac890bdbe85bc08)

## Make a clip

1. Choose a **Voice**. Each voice lists its accent, age and gender. Choose
   **Play sample** to hear it first.
2. Type what the voice should say in **Script**, up to 10,000 characters. Tags
   in square brackets, such as `[whispering]`, direct how a line is spoken.
3. Under **Output**, choose a **Delivery** style (**Creative**, **Natural** or
   **Robust**) and a format: WAV at 44.1 kHz or MP3 at 192 kbps.
4. Check **Cost**, then choose **Generate**.

Your clip appears in **Generations**. Filter the list to **Audio** to see only
clips.

![A finished speech clip in Generations, named after its script, with its Eleven v4 and speech tags.](https://mintcdn.com/zero-gen/m4I7fPs1rAXZSMjU/images/generate/audio-result.png?fit=max\&auto=format\&n=m4I7fPs1rAXZSMjU\&q=85\&s=738ebc51b3e61bdf65b480942f63828b)

ZeroGen names the clip after its script unless you type a **Name** or use a
[naming preset](https://docs.zerogen.com/generate/naming-presets.md).


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.