> ## 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.

# Eleven v4

> ElevenLabs' text-to-speech model, in Generate's audio generator.

Eleven v4, from ElevenLabs, turns a script into speech. It's the model in
Generate's **Audio** generator. See [Make audio](https://docs.zerogen.com/generate/make-audio.md).

## What you give it

* **Script**: up to 10,000 characters. Add audio tags in square brackets,
  such as `[whispering]`, to direct the delivery.
* **Voice**: one of 21 voices. Choose **Play sample** to hear one first.

## Output settings

| Setting | Options |
| - | - |
| Delivery | How steady the voice is: **Creative** is the most expressive and varied, **Robust** the steadiest, and **Natural**, the default, sits between. |
| Format | **WAV · 44.1 kHz**, the default, or **MP3 · 192 kbps**. |

Each run makes one clip.

## Cost

Eleven v4 is priced by the length of the script, per 1,000 characters.
Delivery and format don't change the price. A 1,000-character script costs
about $0.11, and a 10,000-character script about $1.04. Prices are as of
October 28, 2026.


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