# ElevenLabs Provider

The [ElevenLabs](https://elevenlabs.io/) provider contains language model support for the ElevenLabs transcription and speech generation APIs.

## Setup

The ElevenLabs provider is available in the `@ai-sdk/elevenlabs` module. You can install it with

<Tabs items={['pnpm', 'npm', 'yarn', 'bun']}>
  <Tab>
    <Snippet text="pnpm add @ai-sdk/elevenlabs" dark />
  </Tab>
  <Tab>
    <Snippet text="npm install @ai-sdk/elevenlabs" dark />
  </Tab>
  <Tab>
    <Snippet text="yarn add @ai-sdk/elevenlabs" dark />
  </Tab>

  <Tab>
    <Snippet text="bun add @ai-sdk/elevenlabs" dark />
  </Tab>
</Tabs>

## Provider Instance

You can import the default provider instance `elevenlabs` from `@ai-sdk/elevenlabs`:

```ts
import { elevenlabs } from '@ai-sdk/elevenlabs';
```

If you need a customized setup, you can import `createElevenLabs` from `@ai-sdk/elevenlabs` and create a provider instance with your settings:

```ts
import { createElevenLabs } from '@ai-sdk/elevenlabs';

const elevenlabs = createElevenLabs({
  // custom settings, e.g.
  fetch: customFetch,
});
```

You can use the following optional settings to customize the ElevenLabs provider instance:

- **apiKey** _string_

  API key that is being sent using the `Authorization` header.
  It defaults to the `ELEVENLABS_API_KEY` environment variable.

- **headers** _Record&lt;string,string&gt;_

  Custom headers to include in the requests.

- **fetch** _(input: RequestInfo, init?: RequestInit) => Promise&lt;Response&gt;_

  Custom [fetch](https://developer.mozilla.org/en-US/docs/Web/API/fetch) implementation.
  Defaults to the global `fetch` function.
  You can use it as a middleware to intercept requests,
  or to provide a custom fetch implementation for e.g. testing.

## Speech Models

You can create models that call the [ElevenLabs speech API](https://elevenlabs.io/text-to-speech)
using the `.speech()` factory method.

The first argument is the model id e.g. `eleven_multilingual_v2`.

```ts
const model = elevenlabs.speech('eleven_multilingual_v2');
```

You can also pass additional provider-specific options using the `providerOptions` argument. For example, supplying a voice to use for the generated audio.

```ts highlight="6"
import { experimental_generateSpeech as generateSpeech } from 'ai';
import { elevenlabs } from '@ai-sdk/elevenlabs';

const result = await generateSpeech({
  model: elevenlabs.speech('eleven_multilingual_v2'),
  text: 'Hello, world!',
  providerOptions: { elevenlabs: {} },
});
```

- **language_code** _string or null_  
  Optional. Language code (ISO 639-1) used to enforce a language for the model. Currently, only Turbo v2.5 and Flash v2.5 support language enforcement. For other models, providing a language code will result in an error.

- **voice_settings** _object or null_  
  Optional. Voice settings that override stored settings for the given voice. These are applied only to the current request.

  - **stability** _double or null_  
    Optional. Determines how stable the voice is and the randomness between each generation. Lower values introduce broader emotional range; higher values result in a more monotonous voice.
  - **use_speaker_boost** _boolean or null_  
    Optional. Boosts similarity to the original speaker. Increases computational load and latency.
  - **similarity_boost** _double or null_  
    Optional. Controls how closely the AI should adhere to the original voice.
  - **style** _double or null_  
    Optional. Amplifies the style of the original speaker. May increase latency if set above 0.

- **pronunciation_dictionary_locators** _array of objects or null_  
  Optional. A list of pronunciation dictionary locators to apply to the text, in order. Up to 3 locators per request.  
  Each locator object:

  - **pronunciation_dictionary_id** _string_ (required)  
    The ID of the pronunciation dictionary.
  - **version_id** _string or null_ (optional)  
    The version ID of the dictionary. If not provided, the latest version is used.

- **seed** _integer or null_  
  Optional. If specified, the system will attempt to sample deterministically. Must be between 0 and 4294967295. Determinism is not guaranteed.

- **previous_text** _string or null_  
  Optional. The text that came before the current request's text. Can improve continuity when concatenating generations or influence current generation continuity.

- **next_text** _string or null_  
  Optional. The text that comes after the current request's text. Can improve continuity when concatenating generations or influence current generation continuity.

- **previous_request_ids** _array of strings or null_  
  Optional. List of request IDs for samples generated before this one. Improves continuity when splitting large tasks. Max 3 IDs. If both `previous_text` and `previous_request_ids` are sent, `previous_text` is ignored.

- **next_request_ids** _array of strings or null_  
  Optional. List of request IDs for samples generated after this one. Useful for maintaining continuity when regenerating a sample. Max 3 IDs. If both `next_text` and `next_request_ids` are sent, `next_text` is ignored.

- **apply_text_normalization** _enum_  
  Optional. Controls text normalization.  
  Allowed values: `'auto'` (default), `'on'`, `'off'`.

  - `'auto'`: System decides whether to apply normalization (e.g., spelling out numbers).
  - `'on'`: Always apply normalization.
  - `'off'`: Never apply normalization.  
    For `eleven_turbo_v2_5` and `eleven_flash_v2_5`, can only be enabled with Enterprise plans.

- **apply_language_text_normalization** _boolean_  
  Optional. Defaults to `false`. Controls language text normalization, which helps with proper pronunciation in some supported languages (currently only Japanese). May significantly increase latency.

### Model Capabilities

| Model                    | Instructions        |
| ------------------------ | ------------------- |
| `eleven_v3`              | <Check size={18} /> |
| `eleven_multilingual_v2` | <Check size={18} /> |
| `eleven_flash_v2_5`      | <Check size={18} /> |
| `eleven_flash_v2`        | <Check size={18} /> |
| `eleven_turbo_v2_5`      | <Check size={18} /> |
| `eleven_turbo_v2`        | <Check size={18} /> |
| `eleven_monolingual_v1`  | <Check size={18} /> |
| `eleven_multilingual_v1` | <Check size={18} /> |

## Transcription Models

You can create models that call the [ElevenLabs transcription API](https://elevenlabs.io/speech-to-text)
using the `.transcription()` factory method.

The first argument is the model id e.g. `scribe_v1`.

```ts
const model = elevenlabs.transcription('scribe_v1');
```

You can also pass additional provider-specific options using the `providerOptions` argument. For example, supplying the input language in ISO-639-1 (e.g. `en`) format can sometimes improve transcription performance if known beforehand.

```ts highlight="6"
import { experimental_transcribe as transcribe } from 'ai';
import { elevenlabs } from '@ai-sdk/elevenlabs';

const result = await transcribe({
  model: elevenlabs.transcription('scribe_v1'),
  audio: new Uint8Array([1, 2, 3, 4]),
  providerOptions: { elevenlabs: { languageCode: 'en' } },
});
```

The following provider options are available:

- **languageCode** _string_

  An ISO-639-1 or ISO-639-3 language code corresponding to the language of the audio file.
  Can sometimes improve transcription performance if known beforehand.
  Defaults to `null`, in which case the language is predicted automatically.

- **tagAudioEvents** _boolean_

  Whether to tag audio events like (laughter), (footsteps), etc. in the transcription.
  Defaults to `true`.

- **numSpeakers** _integer_

  The maximum amount of speakers talking in the uploaded file.
  Can help with predicting who speaks when.
  The maximum amount of speakers that can be predicted is 32.
  Defaults to `null`, in which case the amount of speakers is set to the maximum value the model supports.

- **timestampsGranularity** _enum_

  The granularity of the timestamps in the transcription.
  Defaults to `'word'`.
  Allowed values: `'none'`, `'word'`, `'character'`.

- **diarize** _boolean_

  Whether to annotate which speaker is currently talking in the uploaded file.
  Defaults to `true`.

- **fileFormat** _enum_

  The format of input audio.
  Defaults to `'other'`.
  Allowed values: `'pcm_s16le_16'`, `'other'`.
  For `'pcm_s16le_16'`, the input audio must be 16-bit PCM at a 16kHz sample rate, single channel (mono), and little-endian byte order.
  Latency will be lower than with passing an encoded waveform.

### Model Capabilities

| Model                    | Transcription       | Duration            | Segments            | Language            |
| ------------------------ | ------------------- | ------------------- | ------------------- | ------------------- |
| `scribe_v1`              | <Check size={18} /> | <Check size={18} /> | <Check size={18} /> | <Check size={18} /> |
| `scribe_v1_experimental` | <Check size={18} /> | <Check size={18} /> | <Check size={18} /> | <Check size={18} /> |


## Navigation

- [AI Gateway](/v5/providers/ai-sdk-providers/ai-gateway)
- [xAI Grok](/v5/providers/ai-sdk-providers/xai)
- [Vercel](/v5/providers/ai-sdk-providers/vercel)
- [OpenAI](/v5/providers/ai-sdk-providers/openai)
- [Azure OpenAI](/v5/providers/ai-sdk-providers/azure)
- [Anthropic](/v5/providers/ai-sdk-providers/anthropic)
- [Amazon Bedrock](/v5/providers/ai-sdk-providers/amazon-bedrock)
- [Groq](/v5/providers/ai-sdk-providers/groq)
- [Fal](/v5/providers/ai-sdk-providers/fal)
- [AssemblyAI](/v5/providers/ai-sdk-providers/assemblyai)
- [DeepInfra](/v5/providers/ai-sdk-providers/deepinfra)
- [Deepgram](/v5/providers/ai-sdk-providers/deepgram)
- [Black Forest Labs](/v5/providers/ai-sdk-providers/black-forest-labs)
- [Gladia](/v5/providers/ai-sdk-providers/gladia)
- [LMNT](/v5/providers/ai-sdk-providers/lmnt)
- [Google Generative AI](/v5/providers/ai-sdk-providers/google-generative-ai)
- [Hume](/v5/providers/ai-sdk-providers/hume)
- [Google Vertex AI](/v5/providers/ai-sdk-providers/google-vertex)
- [Rev.ai](/v5/providers/ai-sdk-providers/revai)
- [Baseten](/v5/providers/ai-sdk-providers/baseten)
- [Hugging Face](/v5/providers/ai-sdk-providers/huggingface)
- [Mistral AI](/v5/providers/ai-sdk-providers/mistral)
- [Together.ai](/v5/providers/ai-sdk-providers/togetherai)
- [Cohere](/v5/providers/ai-sdk-providers/cohere)
- [Fireworks](/v5/providers/ai-sdk-providers/fireworks)
- [DeepSeek](/v5/providers/ai-sdk-providers/deepseek)
- [Moonshot AI](/v5/providers/ai-sdk-providers/moonshotai)
- [Alibaba](/v5/providers/ai-sdk-providers/alibaba)
- [Cerebras](/v5/providers/ai-sdk-providers/cerebras)
- [Replicate](/v5/providers/ai-sdk-providers/replicate)
- [Perplexity](/v5/providers/ai-sdk-providers/perplexity)
- [Luma](/v5/providers/ai-sdk-providers/luma)
- [ElevenLabs](/v5/providers/ai-sdk-providers/elevenlabs)


[Full Sitemap](/sitemap.md)