Quickstart

import { AssemblyAI } from "assemblyai";

const baseUrl = "https://api.assemblyai.com";

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

// Use a publicly-accessible URL
const audioFile = "https://assembly.ai/wildfires.mp3";

// Or use a local file:
// const audioFile = "./example.mp3";

const params = {
  audio: audioFile,
  speech_models: ["universal-3-pro", "universal-2"],
  language_detection: true,
  speaker_labels: true,
};

const run = async () => {
  const transcript = await client.transcripts.transcribe(params);

  if (transcript.status === "error") {
    throw new Error(`Transcription failed: ${transcript.error}`);
  }

  // Log transcript.id for every request (not just errors), with a timestamp and API region.
  // It's required to fetch results, retry, or delete the transcript later, and it's the first
  // thing support@assemblyai.com asks for. Delete: /pre-recorded-audio/delete-transcripts
  // Troubleshooting: /pre-recorded-audio/guides/common_errors_and_solutions

  console.log(`\nFull Transcript:\n\n${transcript.text}`);

  // Optionally print speaker diarization results
  // for (const utterance of transcript.utterances) {
  //   console.log(`Speaker ${utterance.speaker}: ${utterance.text}`);
  // }
};

run();

import os
import requests
import time

base_url = "https://api.assemblyai.com"
headers = {"authorization": os.environ["ASSEMBLYAI_API_KEY"]}

# Use a publicly-accessible URL
audio_file = "https://assembly.ai/wildfires.mp3"

# Or upload a local file:
# with open("./example.mp3", "rb") as f:
#     response = requests.post(base_url + "/v2/upload", headers=headers, data=f)
#     if response.status_code != 200:
#         print(f"Error: {response.status_code}, Response: {response.text}")
#         response.raise_for_status()
#     upload_json = response.json()
#     audio_file = upload_json["upload_url"]

data = {
    "audio_url": audio_file,
    "speech_models": ["universal-3-pro", "universal-2"],
    "language_detection": True,
    "speaker_labels": True
}

response = requests.post(base_url + "/v2/transcript", headers=headers, json=data)

if response.status_code != 200:
    print(f"Error: {response.status_code}, Response: {response.text}")
    response.raise_for_status()

transcript_json = response.json()
transcript_id = transcript_json["id"]
polling_endpoint = f"{base_url}/v2/transcript/{transcript_id}"

while True:
    transcript = requests.get(polling_endpoint, headers=headers).json()
    if transcript["status"] == "completed":
        print(f"\nFull Transcript:\n\n{transcript['text']}")

        # Optionally print speaker diarization results
        # for utterance in transcript['utterances']:
        #     print(f"Speaker {utterance['speaker']}: {utterance['text']}")
        break
    elif transcript["status"] == "error":
        raise RuntimeError(f"Transcription failed: {transcript['error']}")
    else:
        time.sleep(3)

const baseUrl = "https://api.assemblyai.com";

const headers = {
  authorization: process.env.ASSEMBLYAI_API_KEY,
};

async function transcribe() {
  // Use a publicly-accessible URL
  const audioFile = "https://assembly.ai/wildfires.mp3";

  // Or upload a local file:
  // import fs from "fs-extra";
  // const audioData = await fs.readFile("./example.mp3");
  // const uploadRes = await fetch(`${baseUrl}/v2/upload`, {
  //   method: "POST",
  //   headers,
  //   body: audioData,
  // });
  // if (!uploadRes.ok) throw new Error(`Error: ${uploadRes.status}`);
  // const uploadResponse = await uploadRes.json();
  // const audioFile = uploadResponse.upload_url;

  const data = {
    audio_url: audioFile,
    speech_models: ["universal-3-pro", "universal-2"],
    language_detection: true,
    speaker_labels: true,
  };

  let res = await fetch(`${baseUrl}/v2/transcript`, {
    method: "POST",
    headers: { ...headers, "Content-Type": "application/json" },
    body: JSON.stringify(data),
  });
  if (!res.ok) throw new Error(`Error: ${res.status}`);
  const transcriptResponse = await res.json();
  const transcriptId = transcriptResponse.id;
  const pollingEndpoint = `${baseUrl}/v2/transcript/${transcriptId}`;

  while (true) {
    res = await fetch(pollingEndpoint, { headers });
    if (!res.ok) throw new Error(`Error: ${res.status}`);
    const transcript = await res.json();

    if (transcript.status === "completed") {
      console.log(`\nFull Transcript:\n\n${transcript.text}`);

      // Optionally print speaker diarization results
      // for (const utterance of transcript.utterances) {
      //   console.log(`Speaker ${utterance.speaker}: ${utterance.text}`);
      // }
      break;
    } else if (transcript.status === "error") {
      throw new Error(`Transcription failed: ${transcript.error}`);
    } else {
      await new Promise((resolve) => setTimeout(resolve, 3000));
    }
  }
}

transcribe();