> ## Documentation Index
> Fetch the complete documentation index at: https://langchain-5e9cc07a-preview-update-1770920925-e15dbde.mintlify.site/llms.txt
> Use this file to discover all available pages before exploring further.

# Sonix audio integration

> Integrate with the Sonix audio document loader using LangChain JavaScript.

<Tip>
  **Compatibility**

  Only available on Node.js.
</Tip>

This covers how to load document objects from an audio file using the [Sonix](https://sonix.ai/) API.

## Setup

To run this loader you will need to create an account on the [https://sonix.ai/](https://sonix.ai/) and obtain an auth key from the [https://my.sonix.ai/api](https://my.sonix.ai/api) page.

You'll also need to install the `sonix-speech-recognition` library:

```bash npm theme={null}
npm install @langchain/community @langchain/core sonix-speech-recognition
```

## Usage

Once auth key is configured, you can use the loader to create transcriptions and then convert them into a Document.
In the `request` parameter, you can either specify a local file by setting `audioFilePath` or a remote file using `audioUrl`.
You will also need to specify the audio language. See the list of supported languages [here](https://sonix.ai/docs/api#languages).

```typescript theme={null}
import { SonixAudioTranscriptionLoader } from "@langchain/community/document_loaders/web/sonix_audio";

const loader = new SonixAudioTranscriptionLoader({
  sonixAuthKey: "SONIX_AUTH_KEY",
  request: {
    audioFilePath: "LOCAL_AUDIO_FILE_PATH",
    fileName: "FILE_NAME",
    language: "en",
  },
});

const docs = await loader.load();

console.log(docs);
```

***

<Callout icon="pen-to-square" iconType="regular">
  [Edit this page on GitHub](https://github.com/langchain-ai/docs/edit/main/src/oss/javascript/integrations/document_loaders/web_loaders/sonix_audio_transcription.mdx) or [file an issue](https://github.com/langchain-ai/docs/issues/new/choose).
</Callout>

<Tip icon="terminal" iconType="regular">
  [Connect these docs](/use-these-docs) to Claude, VSCode, and more via MCP for real-time answers.
</Tip>