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

# ElevenLabs

> ElevenLabs voice AI models available through the Hicap API

All ElevenLabs models below are accessible through the **Hicap API**. ElevenLabs provides industry-leading text-to-speech (TTS) and speech-to-text (STT) capabilities. For pricing, see the [Model Catalog](https://hicap.ai/models).

## Text-to-Speech Models

### eleven\_multilingual\_v2

Eleven Multilingual v2 is ElevenLabs' flagship multilingual text-to-speech model, supporting 29 languages with natural-sounding, expressive voice synthesis. It delivers high-quality speech with nuanced prosody and emotional range.

<div className="text-white font-bold">Best for:</div>

<div className="bg-gray-200 dark:bg-black px-3 py-1 mt-2">
  <span>
    Multilingual voice applications, audiobook narration, content localization, accessibility features, and customer-facing voice experiences where natural speech quality is essential.
  </span>
</div>

| Input  |   | Output  |
| ------ | - | ------- |
| `Text` |   | `Audio` |

<Columns cols={1}>
  <div>
    <div className="text-white font-bold">This model offers</div>

    <ul className="mb-6">
      <li>\* 10,000 character context window</li>
      <li>\* 29 language support</li>
    </ul>
  </div>
</Columns>

### eleven\_v3

Eleven v3 is the latest generation ElevenLabs TTS model, delivering improved voice quality, faster generation, and enhanced expressiveness in a compact context window.

<div className="text-white font-bold">Best for:</div>

<div className="bg-gray-200 dark:bg-black px-3 py-1 mt-2">
  <span>
    Real-time voice assistants, interactive applications, short-form content, and latency-sensitive voice experiences where fast generation matters.
  </span>
</div>

| Input  |   | Output  |
| ------ | - | ------- |
| `Text` |   | `Audio` |

<Columns cols={1}>
  <div>
    <div className="text-white font-bold">This model offers</div>

    <ul className="mb-6">
      <li>\* 5,000 character context window</li>
    </ul>
  </div>
</Columns>

## Speech-to-Text Models

### scribe\_v1

Scribe v1 is ElevenLabs' speech-to-text transcription model, supporting 90+ languages with accurate transcription of spoken audio into text.

<div className="text-white font-bold">Best for:</div>

<div className="bg-gray-200 dark:bg-black px-3 py-1 mt-2">
  <span>
    Audio transcription, meeting notes, podcast indexing, subtitle generation, and voice-to-text workflows across multiple languages.
  </span>
</div>

| Input   |   | Output |
| ------- | - | ------ |
| `Audio` |   | `Text` |

<Columns cols={1}>
  <div>
    <div className="text-white font-bold">This model offers</div>

    <ul className="mb-6">
      <li>\* 90+ language support</li>
    </ul>
  </div>
</Columns>

### scribe\_v2

Scribe v2 is the latest generation of ElevenLabs' transcription model, offering improved accuracy and language coverage over Scribe v1.

<div className="text-white font-bold">Best for:</div>

<div className="bg-gray-200 dark:bg-black px-3 py-1 mt-2">
  <span>
    High-accuracy transcription, professional media workflows, real-time captioning, and enterprise audio processing where transcription quality is critical.
  </span>
</div>

| Input   |   | Output |
| ------- | - | ------ |
| `Audio` |   | `Text` |

<Columns cols={1}>
  <div>
    <div className="text-white font-bold">This model offers</div>

    <ul className="mb-6">
      <li>\* 90+ language support</li>
    </ul>
  </div>
</Columns>