Announcing the AssemblyAI Node SDK 2.0

We're thrilled to release version 2.0 of the AssemblyAI Node SDK. The SDK has been rewritten from scratch using TypeScript and provides easy-to-use access to our API. You can use the SDK from Node.js (or a compatible framework) and enjoy an intuitive SDK with typed documentation whether you're using JavaScript or TypeScript.

Here are 3 samples of how you can use the new SDK.

1. Transcribe an audio or video file:

import { AssemblyAI } from "assemblyai";

const client = new AssemblyAI({
  apiKey: process.env.ASSEMBLYAI_API_KEY,
})

const transcript = await client.transcripts.create({
  audio_url: './news.mp4',
})
console.log(transcript.text)

Learn how to transcribe audio by following this step-by-step guide.

2. Talk to your audio data using LeMUR:

const { response } = await client.lemur.questionAnswer({
  transcript_ids: [transcript.id],
  questions: [
    {
      question: 'What are the highlights of the newscast?',
      answer_format: 'text',
    }
  ]
})
console.log(response[0].question, response[0].answer)

With just a few lines of code, you can quickly transcribe your audio asynchronously and use LLMs on top of your spoken audio data using LeMUR.

3. Transcribe audio in real-time:

const rt = client.realtime.createService();

rt.on("transcript", (transcript: TranscriptMessage) => console.log('Transcript:', transcript));
rt.on("error", (error: Error) => console.error('Error', error));
rt.on("close", (code: number, reason: string) => console.log('Closed', code, reason));

await rt.connect();

// Pseudo code for getting audio from a microphone for example
getAudio((chunk) => {
  rt.sendAudio(chunk);
});

await rt.close();

Learn how to transcribe audio in real-time coming from a microphone by following this step-by-step guide.

To learn more about the SDK, check out the GitHub repository README and the AssemblyAI documentation.