Quickstart

Install the HUMAIN Voice SDK and transcribe your first recording in about five minutes.

You install the SDK, transcribe a WAV recording, and get the transcript plus WebVTT captions.

Before you start

  • An API key from the HUMAIN Voice console (Authentication).
  • A WAV recording saved as recording.wav.
  • Node.js 24 or newer (runs .ts files directly) or Python 3.10 or newer.

1. Install the SDK

npm install @humain-voice/[email protected]

2. Set your environment

export API_URL="https://api.voice.humain.com"
export API_KEY="YOUR_API_KEY"

Socket.IO examples also read the optional API_PATH (Connection settings).

3. Run a batch transcription

batch-transcription.ts
import { readFile, writeFile } from 'node:fs/promises';

import {
  BatchDiarization,
  BatchTranscribeClient,
  BatchTranscriptionModel,
  Language,
  Subtitles,
} from '@humain-voice/sdk';

function requiredEnv(name: 'API_KEY' | 'API_URL'): string {
  const value = process.env[name];
  if (!value) throw new Error(`${name} is required`);
  return value;
}

async function main(): Promise<void> {
  const inputPath = process.argv[2] ?? 'recording.wav';
  const outputPath = process.argv[3] ?? 'recording.vtt';
  const client = new BatchTranscribeClient({
    api_url: requiredEnv('API_URL'),
    api_key: requiredEnv('API_KEY'),
    api_version: process.env.API_VERSION ?? 'v1',
  });

  try {
    const result = await client.transcribe(
      await readFile(inputPath),
      Language.ArEn,
      {
        asr: BatchTranscriptionModel.BayanArEn,
        diarization: BatchDiarization.On,
        saveResult: true,
        pollInterval: 2,
        timeout: 300,
        onProgress: ({ status }) => console.info('status:', status),
      },
    );

    console.info(result.results?.transcript ?? '');
    await writeFile(outputPath, Subtitles.fromResponse(result).toVtt(), 'utf8');
  } finally {
    await client.close();
  }
}

void main().catch((error: unknown) => {
  console.error(error);
  process.exitCode = 1;
});

Save the example under its displayed filename and run it:

  • JavaScript / TypeScript: node batch-transcription.ts recording.wav
  • Python: python batch_transcription.py recording.wav

What you get back

Expected output (illustrative):

status: queued
status: processing
status: processing
status: done
Hello and welcome to the meeting.

Captions are written to recording.vtt. The upload runs as a job with its own statuses (Batch is a job).

Next steps

On this page