Skip to main content

Open AI Whisper 音频

¥Open AI Whisper Audio

Compatibility

仅在 Node.js 上可用。

¥Only available on Node.js.

本概述如何使用 Open AI Whisper API 从音频文件加载文档对象。

¥This covers how to load document objects from an audio file using the Open AI Whisper API.

设置​

¥Setup

要运行此加载器，你需要在 Open AI 上创建一个账户，并从 https://platform.openai.com/account 页面获取授权密钥。

¥To run this loader you will need to create an account on the Open AI and obtain an auth key from the https://platform.openai.com/account page.

用法​

¥Usage

配置好授权密钥后，你可以使用加载器创建转录，然后将其转换为文档。

¥Once auth key is configured, you can use the loader to create transcriptions and then convert them into a Document.

import { OpenAIWhisperAudio } from "@langchain/community/document_loaders/fs/openai_whisper_audio";

const filePath = "./src/document_loaders/example_data/test.mp3";

const loader = new OpenAIWhisperAudio(filePath, {
  transcriptionCreateParams: {
    language: "en",
  },
});

const docs = await loader.load();

console.log(docs);

API Reference: