Sign inDemoInstall


Package Overview
File Explorer

Advanced tools

Install Socket

Detect and block malicious and high-risk dependencies



Version published




  • Add more TSDoc comments for RealtimeService documentation
  • Add new LeMUR models
  • Add TranscriptWebhookNotification which is a union of TranscriptReadyNotification or RedactedAudioNotification
  • Add RedactedAudioNotification which represents the body of the PII redacted audio webhook notification.



npm Test GitHub License AssemblyAI Twitter AssemblyAI YouTube Discord

AssemblyAI JavaScript SDK

The AssemblyAI JavaScript SDK provides an easy-to-use interface for interacting with the AssemblyAI API, which supports async and real-time transcription, as well as the latest LeMUR models. It is written primarily for Node.js in TypeScript with all types exported, but also compatible with other runtimes.


Visit the AssemblyAI documentation for step-by-step instructions and a lot more details about our AI models and API. Explore the SDK API reference for more details on the SDK types, functions, and classes.


Install the AssemblyAI SDK using your preferred package manager:

npm install assemblyai
yarn add assemblyai
pnpm add assemblyai
bun add assemblyai

Then, import the assemblyai module and create an AssemblyAI object with your API key:

import { AssemblyAI } from "assemblyai";

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

You can now use the client object to interact with the AssemblyAI API.

Using a CDN

You can use automatic CDNs like UNPKG to load the library from a script tag.

  • Replace :version with the desired version or latest.
  • Remove .min to load the non-minified version.
  • Remove .streaming to load the entire SDK. Keep .streaming to load the Streaming STT specific version.
<!-- Unminified full SDK -->
<script src=""></script>
<!-- Minified full SDK -->
<script src=""></script>
<!-- Unminified Streaming STT only -->
<script src=""></script>
<!-- Minified Streaming STT only -->
<script src=""></script>

The script creates a global assemblyai variable containing all the services. Here's how you create a RealtimeTranscriber object.

const { RealtimeTranscriber } = assemblyai;
const transcriber = new RealtimeTranscriber({

For type support in your IDE, see Reference types from JavaScript.


Transcribe audio and video files

Transcribe an audio file with a public URL

When you create a transcript, you can either pass in a URL to an audio file or upload a file directly.

// Transcribe file at remote URL
let transcript = await client.transcripts.transcribe({
  audio: "",

Note You can also pass a local file path, a stream, or a buffer as the audio property.

transcribe queues a transcription job and polls it until the status is completed or error.

If you don't want to wait until the transcript is ready, you can use submit:

let transcript = await client.transcripts.submit({
  audio: "",
Transcribe a local audio file

When you create a transcript, you can either pass in a URL to an audio file or upload a file directly.

// Upload a file via local path and transcribe
let transcript = await client.transcripts.transcribe({
  audio: "./news.mp4",

Note: You can also pass a file URL, a stream, or a buffer as the audio property.

transcribe queues a transcription job and polls it until the status is completed or error.

If you don't want to wait until the transcript is ready, you can use submit:

let transcript = await client.transcripts.submit({
  audio: "./news.mp4",
Enable additional AI models

You can extract even more insights from the audio by enabling any of our AI models using transcription options. For example, here's how to enable Speaker diarization model to detect who said what.

let transcript = await client.transcripts.transcribe({
  audio: "",
  speaker_labels: true,
for (let utterance of transcript.utterances) {
  console.log(`Speaker ${utterance.speaker}: ${utterance.text}`);
Get a transcript

This will return the transcript object in its current state. If the transcript is still processing, the status field will be queued or processing. Once the transcript is complete, the status field will be completed.

const transcript = await client.transcripts.get(;

If you created a transcript using .submit(), you can still poll until the transcript status is completed or error using .waitUntilReady():

const transcript = await client.transcripts.waitUntilReady(, {
  // How frequently the transcript is polled in ms. Defaults to 3000.
  pollingInterval: 1000,
  // How long to wait in ms until the "Polling timeout" error is thrown. Defaults to infinite (-1).
  pollingTimeout: 5000,
Get sentences and paragraphs
const sentences = await client.transcripts.sentences(;
const paragraphs = await client.transcripts.paragraphs(;
Get subtitles
const charsPerCaption = 32;
let srt = await client.transcripts.subtitles(, "srt");
srt = await client.transcripts.subtitles(, "srt", charsPerCaption);

let vtt = await client.transcripts.subtitles(, "vtt");
vtt = await client.transcripts.subtitles(, "vtt", charsPerCaption);
List transcripts

This will return a page of transcripts you created.

const page = await client.transcripts.list();

You can also paginate over all pages.

let previousPageUrl: string | null = null;
do {
  const page = await client.transcripts.list(previousPageUrl);
  previousPageUrl = page.page_details.prev_url;
} while (previousPageUrl !== null);

[!NOTE] To paginate over all pages, you need to use the page.page_details.prev_url because the transcripts are returned in descending order by creation date and time. The first page is are the most recent transcript, and each "previous" page are older transcripts.

Delete a transcript
const res = await client.transcripts.delete(;

Transcribe in real-time

Create the real-time transcriber.

const rt = client.realtime.transcriber();

You can also pass in the following options.

const rt = client.realtime.transcriber({
  realtimeUrl: 'wss://localhost/override',
  apiKey: process.env.ASSEMBLYAI_API_KEY // The API key passed to `AssemblyAI` will be used by default,
  sampleRate: 16_000,
  wordBoost: ['foo', 'bar']

[!WARNING] Storing your API key in client-facing applications exposes your API key. Generate a temporary auth token on the server and pass it to your client. Server code:

const token = await client.realtime.createTemporaryToken({ expires_in = 60 });
// TODO: return token to client

Client code:

import { RealtimeTranscriber } from "assemblyai"; // or "assemblyai/streaming"
// TODO: implement getToken to retrieve token from server
const token = await getToken();
const rt = new RealtimeTranscriber({

You can configure the following events.

rt.on("open", ({ sessionId, expiresAt }) => console.log('Session ID:', sessionId, 'Expires at:', expiresAt));
rt.on("close", (code: number, reason: string) => console.log('Closed', code, reason));
rt.on("transcript", (transcript: TranscriptMessage) => console.log('Transcript:', transcript));
rt.on("transcript.partial", (transcript: PartialTranscriptMessage) => console.log('Partial transcript:', transcript));
rt.on("", (transcript: FinalTranscriptMessage) => console.log('Final transcript:', transcript));
rt.on("error", (error: Error) => console.error('Error', error));

After configuring your events, connect to the server.

await rt.connect();

Send audio data via chunks.

// Pseudo code for getting audio
getAudio((chunk) => {

Or send audio data via a stream by piping to the real-time stream.


Close the connection when you're finished.

await rt.close();

Apply LLMs to your audio with LeMUR

Call LeMUR endpoints to apply LLMs to your transcript.

Prompt your audio with LeMUR
const { response } = await client.lemur.task({
  transcript_ids: ["0d295578-8c75-421a-885a-2c487f188927"],
  prompt: "Write a haiku about this conversation.",
Summarize with LeMUR
const { response } = await client.lemur.summary({
  transcript_ids: ["0d295578-8c75-421a-885a-2c487f188927"],
  answer_format: "one sentence",
  context: {
    speakers: ["Alex", "Bob"],
Ask questions
const { response } = await client.lemur.questionAnswer({
  transcript_ids: ["0d295578-8c75-421a-885a-2c487f188927"],
  questions: [
      question: "What are they discussing?",
      answer_format: "text",
Generate action items
const { response } = await client.lemur.actionItems({
  transcript_ids: ["0d295578-8c75-421a-885a-2c487f188927"],
Delete LeMUR request
const response = await client.lemur.purgeRequestData(lemurResponse.request_id);


If you want to contribute to the JavaScript SDK, follow the guidelines in



Last updated on 10 Jul 2024

Did you know?


Socket for GitHub automatically highlights issues in each pull request and monitors the health of all your open source dependencies. Discover the contents of your packages and block harmful activity before you install or update your dependencies.


Related posts

SocketSocket SOC 2 Logo


  • Package Alerts
  • Integrations
  • Docs
  • Pricing
  • FAQ
  • Roadmap


Stay in touch

Get open source security insights delivered straight into your inbox.

  • Terms
  • Privacy
  • Security

Made with ⚡️ by Socket Inc