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

# Eleven Speech: lifelike text to speech

> Generate directable speech with Eleven Speech (Eleven v4) on Mage, in 16 voices and 90+ languages. Short scripts run unlimited from Basic; longer ones need Pro, Pro Plus, or Max.

Eleven Speech is ElevenLabs' text-to-speech model on Mage. It reads your text in one of 16 voices, in more than 90 languages, and takes direction from audio tags written in square brackets. Its current model is **Eleven v4**.

## Overview

| Detail | |
| - | - |
| Type | Audio |
| Origin | Run by ElevenLabs, reached via Mage |
| Models | Eleven v4 |
| Unlimited from | Basic |

## Unlimited generation by plan

Eleven Speech is priced by the length of the text it speaks, audio tags included: 30 Gems for each started block of 250 characters.

| Model | Setting | Basic | Pro | Pro Plus | Max |
| - | - | - | - | - | - |
| Eleven v4 | Up to 750 characters | Unlimited | Unlimited | Unlimited | Unlimited |
| Eleven v4 | Up to 1,500 characters | Gems | Unlimited | Unlimited | Unlimited |
| Eleven v4 | Up to 3,250 characters | Gems | Gems | Unlimited | Unlimited |
| Eleven v4 | Up to 4,750 characters | Gems | Gems | Gems | Unlimited |
| Eleven v4 | Longer | Gems | Gems | Gems | Gems |

## What it supports on Mage

| Feature | Support |
| - | - |
| Image references | No |
| Audio references | No |
| Voices | 16 preset voices |
| Text length | Up to 5,000 characters |

## Best for

* Narration, voiceover, and character lines that need real acting
* Speech in languages other than English
* Sound cues placed inside the speech

## Directing it with audio tags

Write a tag in square brackets before the line it should change. Tags can set emotion (`[excited]`, `[sarcastic]`), delivery (`[whispers]`, `[shouting]`), reactions (`[laughs]`, `[sighs]`), and sound cues (`[applause]`, `[door slams]`). Be specific: `[low, gravelly voice]` works better than a vague tag, which the model may read as a sound effect.

```text theme={null}
[whispers] Did you hear that? [excited] It is them. They actually came back!
```

**Stability** controls how much the performance varies: lower values are more expressive, higher values keep the delivery steady.

## Limitations

* It speaks in its preset voices only; it does not take a voice from an audio reference yet. For a voice that should recur across video clips, use a [Character Voice](https://docs.mage.space/features/character-voices.md).
* Speech only. For songs, use [Eleven Music](https://docs.mage.space/models/eleven-music.md).

## Use via API

Eleven Speech is available through the [Mage API](https://docs.mage.space/api/overview.md) as the `eleven_speech` architecture. Its fields, tokens, defaults, and price are on [its API reference page](https://docs.mage.space/api/models/eleven_speech.md).


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