Skip to main content
CompatibilityOnly available on Node.js.
This covers how to load document objects from an audio file using the Sonix API.

​
Setup

To run this loader you will need to create an account on the https://sonix.ai/ and obtain an auth key from the https://my.sonix.ai/api page. You’ll also need to install the sonix-speech-recognition library:
npm
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. 
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);
Edit the source of this page on GitHub.
Connect these docs programmatically to Claude, VSCode, and more via MCP for real-time answers.
⌘I