AssemblyAI Core Workflow B — Streaming & LeMUR

Overview

Two advanced workflows: (1) real-time streaming transcription via WebSocket for live captioning and voice agents, and (2) LeMUR for applying LLMs to transcripts — summarization, Q&A, action items, and custom tasks.

Prerequisites

• assemblyai package installed (npm install assemblyai)
• API key configured in ASSEMBLYAIAPIKEY
• For streaming: microphone or audio stream source

Part 1: Real-Time Streaming Transcription

Step 1: Basic Streaming Setup

import { AssemblyAI } from 'assemblyai';

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

const transcriber = client.streaming.createService({
  // Model options: 'nova-3' (default), 'nova-3-pro' (highest accuracy)
  speech_model: 'nova-3',
  sample_rate: 16000,
});

transcriber.on('open', ({ sessionId }) => {
  console.log('Session opened:', sessionId);
});

transcriber.on('transcript', (message) => {
  // message_type: 'PartialTranscript' or 'FinalTranscript'
  if (message.message_type === 'FinalTranscript') {
    console.log('[Final]', message.text);
  } else {
    process.stdout.write(`\r[Partial] ${message.text}`);
  }
});

transcriber.on('error', (error) => {
  console.error('Streaming error:', error);
});

transcriber.on('close', (code, reason) => {
  console.log('Session closed:', code, reason);
});

await transcriber.connect();

// Send audio chunks (16-bit PCM, 16kHz mono)
// transcriber.sendAudio(audioBuffer);

// When done:
// await transcriber.close();

Step 2: Stream from Microphone (Node.js)

import { AssemblyAI } from 'assemblyai';
import { spawn } from 'child_process';

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

const transcriber = client.streaming.createService({
  speech_model: 'nova-3',
  sample_rate: 16000,
});

transcriber.on('transcript', (msg) => {
  if (msg.message_type === 'FinalTranscript' && msg.text) {
    console.log(msg.text);
  }
});

await transcriber.connect();

// Use SoX to capture microphone audio as raw PCM
const mic = spawn('sox', [
  '-d',                  // default audio device
  '-t', 'raw',           // raw PCM output
  '-b', '16',            // 16-bit
  '-r', '16000',         // 16kHz sample rate
  '-c', '1',             // mono
  '-e', 'signed-integer',
  '-',                   // pipe to stdout
]);

mic.stdout.on('data', (chunk: Buffer) => {
  transcriber.sendAudio(chunk);
});

mic.on('close', async () => {
  await 

AssemblyAI Cost Tuning

Overview

Optimize AssemblyAI costs through model selection, feature-aware billing, and usage monitoring. AssemblyAI charges per audio hour with add-on pricing for intelligence features.

Prerequisites

• Access to AssemblyAI billing dashboard at https://www.assemblyai.com/app
• Understanding of current usage patterns

Actual Pricing (Pay-As-You-Go)

Speech-to-Text (Async)

Streaming Speech-to-Text

Audio Intelligence Add-Ons

LeMUR

Instructions

Step 1: Cost Estimation Calculator

interface CostEstimate {
  baseTranscriptionCost: number;
  featuresCost: number;
  totalCost: number;
  breakdown: Record<string, number>;
}

function estimateTranscriptionCost(
  audioHours: number,
  options: {
    model?: 'best' | 'nano';
    speakerLabels?: boolean;
    sentimentAnalysis?: boolean;
    entityDetection?: boolean;
    contentSafety?: boolean;
    iabCategories?: boolean;
    piiRedaction?: boolean;
  } = {}
): CostEstimate {
  const model = options.model ?? 'best';
  const baseRate = model === 'best' ? 0.37 : 0.12;
  const baseCost = audioHours * baseRate;

  const breakdown: Record<string, number> = {
    [`transcription (${model})`]: baseCost,
  };

  let featuresCost = 0;

  if (options.speakerLabels) {
    const cost = audioHours * 0.02;
    breakdown['speaker_labels'] = cost;
    featuresCost += cost;
  }
  if (options.sentimentAnalysis) {
    const cost = audioHours * 0.02;
    breakdown['sentiment_analysis'] = cost;
    feature

AssemblyAI Debug Bundle

Overview

Collect all diagnostic information needed to resolve AssemblyAI issues — SDK version, transcript status, API connectivity, and configuration — packaged for support tickets.

Prerequisites

• assemblyai package installed
• Access to application logs
• Failed transcript ID (if applicable)

Instructions

Step 1: Create Debug Bundle Script

#!/bin/bash
# assemblyai-debug-bundle.sh
set -euo pipefail

BUNDLE_DIR="assemblyai-debug-$(date +%Y%m%d-%H%M%S)"
mkdir -p "$BUNDLE_DIR"

echo "=== AssemblyAI Debug Bundle ===" > "$BUNDLE_DIR/summary.txt"
echo "Generated: $(date -u +%Y-%m-%dT%H:%M:%SZ)" >> "$BUNDLE_DIR/summary.txt"
echo "" >> "$BUNDLE_DIR/summary.txt"

# Environment
echo "--- Runtime ---" >> "$BUNDLE_DIR/summary.txt"
node --version >> "$BUNDLE_DIR/summary.txt" 2>&1 || echo "Node.js not found" >> "$BUNDLE_DIR/summary.txt"
echo "Platform: $(uname -s) $(uname -m)" >> "$BUNDLE_DIR/summary.txt"
echo "ASSEMBLYAI_API_KEY: ${ASSEMBLYAI_API_KEY:+[SET (${#ASSEMBLYAI_API_KEY} chars)]}" >> "$BUNDLE_DIR/summary.txt"
echo "" >> "$BUNDLE_DIR/summary.txt"

# SDK version
echo "--- SDK Version ---" >> "$BUNDLE_DIR/summary.txt"
npm list assemblyai 2>/dev/null >> "$BUNDLE_DIR/summary.txt" || echo "assemblyai not in node_modules" >> "$BUNDLE_DIR/summary.txt"
echo "" >> "$BUNDLE_DIR/summary.txt"

# API connectivity
echo "--- API Connectivity ---" >> "$BUNDLE_DIR/summary.txt"
HTTP_CODE=$(curl -s -o /dev/null -w "%{http_code}" \
  -H "Authorization: ${ASSEMBLYAI_API_KEY:-none}" \
  https://api.assemblyai.com/v2/transcript 2>/dev/null || echo "FAILED")
echo "GET /v2/transcript: HTTP $HTTP_CODE" >> "$BUNDLE_DIR/summary.txt"

STATUS_CODE=$(curl -s -o /dev/null -w "%{http_code}" \
  https://api.assemblyai.com/v2 2>/dev/null || echo "FAILED")
echo "GET /v2: HTTP $STATUS_CODE" >> "$BUNDLE_DIR/summary.txt"
echo "" >> "$BUNDLE_DIR/summary.txt"

# AssemblyAI service status
echo "--- Service Status ---" >> "$BUNDLE_DIR/summary.txt"
curl -s https://status.assemblyai.com/api/v2/status.json 2>/dev/null \
  | python3 -m json.tool 2>/dev/null >> "$BUNDLE_DIR/summary.txt" \
  || echo "Could not fetch status" >> "$BUNDLE_DIR/summary.txt"

# Package bundle
tar -czf "$BUNDLE_DIR.tar.gz" "$BUNDLE_DIR"
rm -rf "$BUNDLE_DIR"
echo ""
ech

AssemblyAI Deploy Integration

Overview

Deploy AssemblyAI-powered transcription services to Vercel (serverless), Google Cloud Run (containers), and Fly.io with proper secrets management and webhook configuration.

Prerequisites

• AssemblyAI API key for production
• Platform CLI installed (vercel, gcloud, or fly)
• Application with working AssemblyAI integration

Instructions

Vercel Deployment (Serverless)

# Add secrets
vercel env add ASSEMBLYAI_API_KEY production
vercel env add ASSEMBLYAI_WEBHOOK_SECRET production

# Deploy
vercel --prod

API Route for Transcription:

// app/api/transcribe/route.ts (Next.js App Router)
import { AssemblyAI } from 'assemblyai';
import { NextRequest, NextResponse } from 'next/server';

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

export async function POST(req: NextRequest) {
  const { audioUrl, features } = await req.json();

  if (!audioUrl) {
    return NextResponse.json({ error: 'audioUrl required' }, { status: 400 });
  }

  // Use submit() + webhook for production (non-blocking)
  const transcript = await client.transcripts.submit({
    audio: audioUrl,
    webhook_url: `${process.env.NEXT_PUBLIC_APP_URL}/api/webhooks/assemblyai`,
    webhook_auth_header_name: 'X-Webhook-Secret',
    webhook_auth_header_value: process.env.ASSEMBLYAI_WEBHOOK_SECRET!,
    speaker_labels: features?.speakerLabels ?? false,
    sentiment_analysis: features?.sentiment ?? false,
  });

  return NextResponse.json({
    transcriptId: transcript.id,
    status: transcript.status,
  });
}

Webhook Handler:

// app/api/webhooks/assemblyai/route.ts
import { AssemblyAI } from 'assemblyai';
import { NextRequest, NextResponse } from 'next/server';

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

export async function POST(req: NextRequest) {
  // Verify webhook authenticity
  const secret = req.headers.get('x-webhook-secret');
  if (secret !== process.env.ASSEMBLYAI_WEBHOOK_SECRET) {
    return NextResponse.json({ error: 'Unauthorized' }, { status: 401 });
  }

  const { transcript_id, status } = await req.json();

  if (status === 'completed') {
    const transcript = await client.transcripts.get(transcript_id);
    // Store transcript, notify user, trigger downstream processing
    console.log(`Transcript ${transcript_id} completed: ${transcript.text?.length} chars`);
  } else if (status === 'error') {
    console.error(`Transcript ${transcript_id} failed`);
  }

  return NextResponse.json({ received: true });
}

Vercel config:

{
  "function

AssemblyAI Hello World

Overview

Minimal working examples demonstrating AssemblyAI's three core capabilities: async transcription, audio intelligence features, and LeMUR (LLM-powered analysis).

Prerequisites

• Completed assemblyai-install-auth setup
• Valid API key configured in ASSEMBLYAIAPIKEY

Instructions

Step 1: Basic Transcription (Remote URL)

import { AssemblyAI } from 'assemblyai';

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

async function transcribeUrl() {
  const transcript = await client.transcripts.transcribe({
    audio: 'https://storage.googleapis.com/aai-web-samples/5_common_sports_702.wav',
  });

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

  console.log('Transcript:', transcript.text);
  console.log('Duration:', transcript.audio_duration, 'seconds');
  console.log('Word count:', transcript.words?.length);
}

transcribeUrl().catch(console.error);

Step 2: Transcribe a Local File

async function transcribeLocal() {
  // The SDK handles upload automatically when you pass a local path
  const transcript = await client.transcripts.transcribe({
    audio: './recording.mp3',
  });

  console.log('Transcript:', transcript.text);

  // Access word-level timestamps
  for (const word of transcript.words ?? []) {
    console.log(`[${word.start}ms - ${word.end}ms] ${word.text} (${word.confidence})`);
  }
}

Step 3: Enable Audio Intelligence Features

async function transcribeWithIntelligence() {
  const transcript = await client.transcripts.transcribe({
    audio: 'https://storage.googleapis.com/aai-web-samples/5_common_sports_702.wav',
    speaker_labels: true,       // Who said what
    auto_highlights: true,       // Key phrases extraction
    sentiment_analysis: true,    // Sentiment per sentence
    entity_detection: true,      // Named entities (people, orgs, locations)
    summarization: true,         // Auto-summary
    summary_model: 'informative',
    summary_type: 'bullets',
  });

  // Speaker diarization
  for (const utterance of transcript.utterances ?? []) {
    console.log(`Speaker ${utterance.speaker}: ${utterance.text}`);
  }

  // Key phrases
  for (const result of transcript.auto_highlights_result?.results ?? []) {
    console.log(`Key phrase: "${result.text}" (mentioned ${result.count} times)`);
  }

  // Sentiment analysis
  for (const result of transcript.sentiment_analysis_results ?? []) {
    console.log(`${result.sentiment}: "${result.text}"`);
  }

  // Summary
  console.log('Summary:', transcript.summary);
}

Step 4: LeMUR