DE

deepgram-webhooks-events

Handles async transcription results from Deepgram via callback URLs. Automates webhook setup for reliable result processing.

Install

mkdir -p .claude/skills/deepgram-webhooks-events && curl -L -o skill.zip "https://agentskills.codes/api/skills/download/8064" && unzip -o skill.zip -d .claude/skills/deepgram-webhooks-events && rm skill.zip

Installs to .claude/skills/deepgram-webhooks-events

Activation

This is the description your AI agent reads to decide when to run this skill — the better it matches your request, the more reliably it fires.

Implement Deepgram callback and webhook handling for async transcription.
73 charsno explicit “when” trigger
Intermediate

Key capabilities

  • Submit async transcription requests with callback URLs
  • Implement webhook servers with signature verification
  • Manage job tracking using Redis
  • Ensure idempotent processing of webhook events
  • Test callback endpoints locally using ngrok

How it works

The skill configures an asynchronous workflow where Deepgram processes audio in the background and sends results to a provided callback URL via POST requests.

Inputs & outputs

You give it
Audio URL and callback endpoint
You get back
Request ID and asynchronous transcription results

When to use deepgram-webhooks-events

  • Implementing async audio transcription callbacks
  • Configuring webhook endpoints for Deepgram events
  • Adding automatic retry logic for transcription status updates

About this skill

Deepgram Webhooks & Callbacks

Overview

Implement async transcription with Deepgram's callback feature. When you pass a callback URL, Deepgram returns a request_id immediately, processes audio in the background, and POSTs results to your endpoint. Supports HTTP and WebSocket callbacks with automatic retry (10 attempts, 30s intervals).

Deepgram Callback Flow

1. Client -> POST /v1/listen?callback=https://you.com/webhook  (with audio)
2. Deepgram -> 200 { request_id: "..." }                       (immediate)
3. Deepgram processes audio asynchronously
4. Deepgram -> POST https://you.com/webhook                    (results)
   Retries up to 10 times (30s delay) on non-2xx response

Instructions

Step 1: Submit Async Transcription

import { createClient } from '@deepgram/sdk';

const deepgram = createClient(process.env.DEEPGRAM_API_KEY!);

async function submitAsync(audioUrl: string, callbackUrl: string) {
  // Deepgram sends transcription via callback URL instead of
  // holding the connection open.
  const { result, error } = await deepgram.listen.prerecorded.transcribeUrl(
    { url: audioUrl },
    {
      model: 'nova-3',
      smart_format: true,
      diarize: true,
      utterances: true,
      callback: callbackUrl,  // Your HTTPS endpoint
      // callback_method: 'put',  // Optional: use PUT instead of POST
    }
  );

  if (error) throw new Error(`Submit failed: ${error.message}`);

  // Deepgram returns immediately with request_id
  const requestId = result.metadata.request_id;
  console.log(`Submitted. Request ID: ${requestId}`);
  console.log(`Results will be POSTed to: ${callbackUrl}`);
  return requestId;
}

// Also works with direct curl:
// curl -X POST 'https://api.deepgram.com/v1/listen?model=nova-3&callback=https://you.com/webhook' \
//   -H "Authorization: Token $DEEPGRAM_API_KEY" \
//   -H "Content-Type: application/json" \
//   -d '{"url":"https://example.com/audio.wav"}'

Step 2: Callback Server

import express from 'express';
import crypto from 'crypto';

const app = express();

// IMPORTANT: Use raw body for HMAC signature verification
app.use('/webhooks/deepgram', express.raw({ type: 'application/json', limit: '50mb' }));

app.post('/webhooks/deepgram', async (req, res) => {
  try {
    // 1. Verify signature (if webhook secret configured)
    const signature = req.headers['x-deepgram-signature'] as string;
    if (process.env.DEEPGRAM_WEBHOOK_SECRET && signature) {
      const expected = crypto
        .createHmac('sha256', process.env.DEEPGRAM_WEBHOOK_SECRET)
        .update(req.body)
        .digest('hex');

      // Timing-safe comparison to prevent timing attacks
      if (!crypto.timingSafeEqual(Buffer.from(signature), Buffer.from(expected))) {
        console.error('Invalid webhook signature');
        return res.status(401).json({ error: 'Invalid signature' });
      }
    }

    // 2. Parse result
    const result = JSON.parse(req.body.toString());
    const requestId = result.metadata?.request_id;
    const transcript = result.results?.channels?.[0]?.alternatives?.[0]?.transcript;
    const duration = result.metadata?.duration;

    console.log(`Callback received: ${requestId}`);
    console.log(`Duration: ${duration}s`);
    console.log(`Transcript: ${transcript?.substring(0, 200)}...`);

    // 3. Process and store
    await processTranscriptionResult(requestId, result);

    // 4. Return 200 — Deepgram retries on non-2xx
    res.status(200).json({ received: true, request_id: requestId });
  } catch (err: any) {
    console.error('Callback processing error:', err.message);
    // Return 500 to trigger Deepgram retry
    res.status(500).json({ error: 'Processing failed' });
  }
});

async function processTranscriptionResult(requestId: string, result: any) {
  const transcript = result.results.channels[0].alternatives[0];

  // Store transcript
  const record = {
    requestId,
    transcript: transcript.transcript,
    confidence: transcript.confidence,
    duration: result.metadata.duration,
    words: transcript.words?.length ?? 0,
    utterances: result.results.utterances?.map((u: any) => ({
      speaker: u.speaker,
      text: u.transcript,
      start: u.start,
      end: u.end,
    })),
    processedAt: new Date().toISOString(),
  };

  // Save to database / notify clients / trigger downstream
  console.log('Processed:', JSON.stringify(record, null, 2));
  return record;
}

Step 3: Job Tracking with Redis

import Redis from 'ioredis';

const redis = new Redis(process.env.REDIS_URL ?? 'redis://localhost:6379');

class TranscriptionJobTracker {
  async submit(requestId: string, metadata: Record<string, any>) {
    await redis.hset(`job:${requestId}`, {
      status: 'processing',
      submittedAt: new Date().toISOString(),
      ...metadata,
    });
    // Auto-expire after 24 hours
    await redis.expire(`job:${requestId}`, 86400);
  }

  async complete(requestId: string, result: any) {
    await redis.hset(`job:${requestId}`, {
      status: 'completed',
      completedAt: new Date().toISOString(),
      transcript: result.results.channels[0].alternatives[0].transcript,
      duration: result.metadata.duration,
    });
    // Publish for real-time notification
    await redis.publish('transcription:complete', JSON.stringify({
      requestId,
      duration: result.metadata.duration,
    }));
  }

  async getStatus(requestId: string) {
    return redis.hgetall(`job:${requestId}`);
  }
}

// Client-facing status endpoint
app.get('/api/transcription/:requestId', async (req, res) => {
  const tracker = new TranscriptionJobTracker();
  const status = await tracker.getStatus(req.params.requestId);

  if (!status || Object.keys(status).length === 0) {
    return res.status(404).json({ error: 'Job not found' });
  }
  res.json(status);
});

Step 4: Client SDK with Submit/Poll/Wait

class AsyncTranscriptionClient {
  private deepgram: ReturnType<typeof createClient>;
  private baseUrl: string;

  constructor(apiKey: string, serverBaseUrl: string) {
    this.deepgram = createClient(apiKey);
    this.baseUrl = serverBaseUrl;
  }

  async submit(audioUrl: string): Promise<string> {
    const callbackUrl = `${this.baseUrl}/webhooks/deepgram`;
    const { result, error } = await this.deepgram.listen.prerecorded.transcribeUrl(
      { url: audioUrl },
      { model: 'nova-3', smart_format: true, diarize: true, callback: callbackUrl }
    );
    if (error) throw error;
    return result.metadata.request_id;
  }

  async poll(requestId: string): Promise<any> {
    const res = await fetch(`${this.baseUrl}/api/transcription/${requestId}`);
    if (res.status === 404) return null;
    return res.json();
  }

  async waitForResult(requestId: string, timeoutMs = 300000): Promise<any> {
    const start = Date.now();
    while (Date.now() - start < timeoutMs) {
      const status = await this.poll(requestId);
      if (status?.status === 'completed') return status;
      if (status?.status === 'failed') throw new Error('Transcription failed');
      await new Promise(r => setTimeout(r, 2000));  // Poll every 2s
    }
    throw new Error('Timeout waiting for transcription');
  }
}

// Usage:
const client = new AsyncTranscriptionClient(
  process.env.DEEPGRAM_API_KEY!,
  'https://your-server.com'
);
const requestId = await client.submit('https://example.com/long-recording.wav');
const result = await client.waitForResult(requestId);

Step 5: Local Testing with ngrok

# Expose local callback server to Deepgram
ngrok http 3000

# Use the ngrok URL as callback
curl -X POST 'https://api.deepgram.com/v1/listen?model=nova-3&callback=https://abc123.ngrok.io/webhooks/deepgram' \
  -H "Authorization: Token $DEEPGRAM_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"url":"https://static.deepgram.com/examples/nasa-podcast.wav"}'

Step 6: Idempotent Processing

// Deepgram retries callbacks — ensure idempotent processing
const processedRequests = new Set<string>();

app.post('/webhooks/deepgram', async (req, res) => {
  const result = JSON.parse(req.body.toString());
  const requestId = result.metadata?.request_id;

  // Skip if already processed
  if (processedRequests.has(requestId)) {
    console.log(`Duplicate callback for ${requestId} — skipping`);
    return res.status(200).json({ received: true, duplicate: true });
  }

  processedRequests.add(requestId);
  // In production, use Redis SET with NX for distributed dedup:
  // const isNew = await redis.set(`processed:${requestId}`, '1', 'NX', 'EX', 86400);
  // if (!isNew) return res.status(200).json({ duplicate: true });

  await processTranscriptionResult(requestId, result);
  res.status(200).json({ received: true });
});

Output

  • Async transcription submission with callback URL
  • Callback server with signature verification
  • Redis-backed job tracking with pub/sub notifications
  • Client SDK with submit/poll/wait pattern
  • Idempotent callback processing
  • Local testing setup with ngrok

Error Handling

IssueCauseSolution
Callback not receivedEndpoint unreachableCheck HTTPS, firewall, use ngrok for local
Duplicate callbacksDeepgram retry after slow responseImplement idempotency with request_id
Invalid signatureWrong webhook secretVerify DEEPGRAM_WEBHOOK_SECRET matches Console
Processing timeoutSlow downstreamReturn 200 immediately, process async
Large payloadLong audio transcriptIncrease express.raw limit

Resources

When not to use it

  • When real-time transcription is required
  • When the server cannot expose a public HTTPS endpoint

Prerequisites

Deepgram API keyHTTPS-enabled callback endpointRedis instance for job tracking

Limitations

  • Requires HTTPS for callback endpoints
  • Endpoints must return 200 within 10 seconds

How it compares

This approach automates the handling of background transcription results compared to manually polling for status updates.

Compared to similar skills

deepgram-webhooks-events side by side with the closest alternatives in the catalog.

SkillInstallsUpdatedSafetyDifficulty
deepgram-webhooks-events (this skill)027dCautionIntermediate
mcporter72moNo flagsIntermediate
calcom-api24moNo flagsIntermediate
developing-genkit-tooling26moNo flagsIntermediate

Try saying

Example prompts that trigger this skill in your AI assistant.

More by jeremylongshore

View all by jeremylongshore

analyzing-logs

jeremylongshore

Analyze application logs to detect performance issues, identify error patterns, and improve stability by extracting key insights.

14123

ollama-setup

jeremylongshore

Configure auto-configure Ollama when user needs local LLM deployment, free AI alternatives, or wants to eliminate hosted API costs. Trigger phrases: "install ollama", "local AI", "free LLM", "self-hosted AI", "replace OpenAI", "no API costs". Use when appropriate context detected. Trigger with relevant phrases based on skill purpose.

1167

backtesting-trading-strategies

jeremylongshore

Backtest crypto and traditional trading strategies against historical data. Calculates performance metrics (Sharpe, Sortino, max drawdown), generates equity curves, and optimizes strategy parameters. Use when user wants to test a trading strategy, validate signals, or compare approaches. Trigger with phrases like "backtest strategy", "test trading strategy", "historical performance", "simulate trades", "optimize parameters", or "validate signals".

1071

generating-database-seed-data

jeremylongshore

Process this skill enables AI assistant to generate realistic test data and database seed scripts for development and testing environments. it uses faker libraries to create realistic data, maintains relational integrity, and allows configurable data volumes. u... Use when working with databases or data models. Trigger with phrases like 'database', 'query', or 'schema'.

1033

cursor-codebase-indexing

jeremylongshore

Execute set up and optimize Cursor codebase indexing. Triggers on "cursor index setup", "codebase indexing", "index codebase", "cursor semantic search". Use when working with cursor codebase indexing functionality. Trigger with phrases like "cursor codebase indexing", "cursor indexing", "cursor".

885

testing-mobile-apps

jeremylongshore

Execute mobile app testing on iOS and Android devices/simulators. Use when performing specialized testing. Trigger with phrases like "test mobile app", "run iOS tests", or "validate Android functionality".

810

You might also like

mcporter

openclaw

Use the mcporter CLI to list, configure, auth, and call MCP servers/tools directly (HTTP or stdio), including ad-hoc servers, config edits, and CLI/type generation.

726

calcom-api

calcom

Interact with the Cal.com API v2 to manage scheduling, bookings, event types, availability, and calendars. Use this skill when building integrations that need to create or manage bookings, check availability, configure event types, or sync calendars with Cal.com's scheduling infrastructure.

216

developing-genkit-tooling

firebase

Best practices for authoring Genkit tooling, including CLI commands and MCP server tools. Covers naming conventions, architectural patterns, and consistency guidelines.

27

vercel-sdk-patterns

jeremylongshore

Execute apply production-ready Vercel SDK patterns for TypeScript and Python. Use when implementing Vercel integrations, refactoring SDK usage, or establishing team coding standards for Vercel. Trigger with phrases like "vercel SDK patterns", "vercel best practices", "vercel code patterns", "idiomatic vercel".

13

replit-webhooks-events

jeremylongshore

Implement Replit webhook signature validation and event handling. Use when setting up webhook endpoints, implementing signature verification, or handling Replit event notifications securely. Trigger with phrases like "replit webhook", "replit events", "replit webhook signature", "handle replit events", "replit notifications".

01

instantly-core-workflow-b

jeremylongshore

Execute Instantly secondary workflow: Core Workflow B. Use when implementing secondary use case, or complementing primary workflow. Trigger with phrases like "instantly secondary workflow", "secondary task with instantly".

00

Search skills

Search the agent skills registry