jeremylongshore

deepgram-local-dev-loop

@jeremylongshore/deepgram-local-dev-loop
jeremylongshore
1,004
123 forks
Updated 1/18/2026
View on GitHub

Configure Deepgram local development workflow with testing and iteration. Use when setting up development environment, configuring test fixtures, or establishing rapid iteration patterns for Deepgram integration. Trigger with phrases like "deepgram local dev", "deepgram development setup", "deepgram test environment", "deepgram dev workflow".

Installation

$skills install @jeremylongshore/deepgram-local-dev-loop
Claude Code
Cursor
Copilot
Codex
Antigravity

Details

Pathplugins/saas-packs/deepgram-pack/skills/deepgram-local-dev-loop/SKILL.md
Branchmain
Scoped Name@jeremylongshore/deepgram-local-dev-loop

Usage

After installing, this skill will be available to your AI coding assistant.

Verify installation:

skills list

Skill Instructions


name: deepgram-local-dev-loop description: | Configure Deepgram local development workflow with testing and iteration. Use when setting up development environment, configuring test fixtures, or establishing rapid iteration patterns for Deepgram integration. Trigger with phrases like "deepgram local dev", "deepgram development setup", "deepgram test environment", "deepgram dev workflow". allowed-tools: Read, Write, Edit, Bash(npm:), Bash(pip:), Grep version: 1.0.0 license: MIT author: Jeremy Longshore jeremy@intentsolutions.io

Deepgram Local Dev Loop

Overview

Set up an efficient local development workflow for Deepgram integration with fast feedback cycles.

Prerequisites

  • Completed deepgram-install-auth setup
  • Node.js 18+ with npm/pnpm or Python 3.10+
  • Sample audio files for testing
  • Environment variables configured

Instructions

Step 1: Create Project Structure

mkdir -p src tests fixtures
touch src/transcribe.ts tests/transcribe.test.ts

Step 2: Set Up Environment Files

# .env.development
DEEPGRAM_API_KEY=your-dev-api-key
DEEPGRAM_MODEL=nova-2

# .env.test
DEEPGRAM_API_KEY=your-test-api-key
DEEPGRAM_MODEL=nova-2

Step 3: Create Test Fixtures

# Download sample audio for testing
curl -o fixtures/sample.wav https://static.deepgram.com/examples/nasa-podcast.wav

Step 4: Set Up Watch Mode

{
  "scripts": {
    "dev": "tsx watch src/transcribe.ts",
    "test": "vitest",
    "test:watch": "vitest --watch"
  }
}

Output

  • Project structure with src, tests, fixtures directories
  • Environment files for development and testing
  • Watch mode scripts for rapid iteration
  • Sample audio fixtures for testing

Error Handling

ErrorCauseSolution
Fixture Not FoundMissing audio fileRun fixture download script
Env Not Loadeddotenv not configuredInstall and configure dotenv
Watch Mode FailsMissing tsxInstall tsx: npm i -D tsx
API Rate LimitedToo many dev requestsUse cached responses in tests

Examples

TypeScript Dev Setup

// src/transcribe.ts
import { createClient } from '@deepgram/sdk';
import { config } from 'dotenv';

config(); // Load .env

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

export async function transcribeAudio(audioPath: string) {
  const audio = await Bun.file(audioPath).arrayBuffer();

  const { result, error } = await deepgram.listen.prerecorded.transcribeFile(
    Buffer.from(audio),
    { model: process.env.DEEPGRAM_MODEL || 'nova-2', smart_format: true }
  );

  if (error) throw error;
  return result.results.channels[0].alternatives[0].transcript;
}

// Dev mode: run with sample
if (import.meta.main) {
  transcribeAudio('./fixtures/sample.wav').then(console.log);
}

Test Setup with Vitest

// tests/transcribe.test.ts
import { describe, it, expect, beforeAll } from 'vitest';
import { transcribeAudio } from '../src/transcribe';

describe('Deepgram Transcription', () => {
  it('should transcribe audio file', async () => {
    const transcript = await transcribeAudio('./fixtures/sample.wav');
    expect(transcript).toBeDefined();
    expect(transcript.length).toBeGreaterThan(0);
  });

  it('should handle empty audio gracefully', async () => {
    await expect(transcribeAudio('./fixtures/empty.wav'))
      .rejects.toThrow();
  });
});

Mock Responses for Testing

// tests/mocks/deepgram.ts
export const mockTranscriptResponse = {
  results: {
    channels: [{
      alternatives: [{
        transcript: 'This is a test transcript.',
        confidence: 0.99,
        words: [
          { word: 'This', start: 0.0, end: 0.2, confidence: 0.99 },
          { word: 'is', start: 0.2, end: 0.3, confidence: 0.99 },
        ]
      }]
    }]
  }
};

Resources

Next Steps

Proceed to deepgram-sdk-patterns for production-ready code patterns.

More by jeremylongshore

View all
oauth-callback-handler
1,004

Oauth Callback Handler - Auto-activating skill for API Integration. Triggers on: oauth callback handler, oauth callback handler Part of the API Integration skill category.

rabbitmq-queue-setup
1,004

Rabbitmq Queue Setup - Auto-activating skill for Backend Development. Triggers on: rabbitmq queue setup, rabbitmq queue setup Part of the Backend Development skill category.

model-evaluation-suite
1,004

evaluating-machine-learning-models: This skill allows Claude to evaluate machine learning models using a comprehensive suite of metrics. It should be used when the user requests model performance analysis, validation, or testing. Claude can use this skill to assess model accuracy, precision, recall, F1-score, and other relevant metrics. Trigger this skill when the user mentions "evaluate model", "model performance", "testing metrics", "validation results", or requests a comprehensive "model evaluation".

neural-network-builder
1,004

building-neural-networks: This skill allows Claude to construct and configure neural network architectures using the neural-network-builder plugin. It should be used when the user requests the creation of a new neural network, modification of an existing one, or assistance with defining the layers, parameters, and training process. The skill is triggered by requests involving terms like "build a neural network," "define network architecture," "configure layers," or specific mentions of neural network types (e.g., "CNN," "RNN," "transformer").