assemblyai-local-dev-loop

Configure AssemblyAI local development with hot reload and testing. Use when setting up a development environment, configuring test workflows, or establishing a fast iteration cycle with AssemblyAI. Trigger with phrases like "assemblyai dev setup", "assemblyai local development", "assemblyai dev environment", "develop with assemblyai".

1,868 stars

Best use case

assemblyai-local-dev-loop is best used when you need a repeatable AI agent workflow instead of a one-off prompt.

Configure AssemblyAI local development with hot reload and testing. Use when setting up a development environment, configuring test workflows, or establishing a fast iteration cycle with AssemblyAI. Trigger with phrases like "assemblyai dev setup", "assemblyai local development", "assemblyai dev environment", "develop with assemblyai".

Teams using assemblyai-local-dev-loop should expect a more consistent output, faster repeated execution, less prompt rewriting.

When to use this skill

  • You want a reusable workflow that can be run more than once with consistent structure.

When not to use this skill

  • You only need a quick one-off answer and do not need a reusable workflow.
  • You cannot install or maintain the underlying files, dependencies, or repository context.

Installation

Claude Code / Cursor / Codex

$curl -o ~/.claude/skills/assemblyai-local-dev-loop/SKILL.md --create-dirs "https://raw.githubusercontent.com/jeremylongshore/claude-code-plugins-plus-skills/main/plugins/saas-packs/assemblyai-pack/skills/assemblyai-local-dev-loop/SKILL.md"

Manual Installation

  1. Download SKILL.md from GitHub
  2. Place it in .claude/skills/assemblyai-local-dev-loop/SKILL.md inside your project
  3. Restart your AI agent — it will auto-discover the skill

How assemblyai-local-dev-loop Compares

Feature / Agentassemblyai-local-dev-loopStandard Approach
Platform SupportNot specifiedLimited / Varies
Context Awareness High Baseline
Installation ComplexityUnknownN/A

Frequently Asked Questions

What does this skill do?

Configure AssemblyAI local development with hot reload and testing. Use when setting up a development environment, configuring test workflows, or establishing a fast iteration cycle with AssemblyAI. Trigger with phrases like "assemblyai dev setup", "assemblyai local development", "assemblyai dev environment", "develop with assemblyai".

Where can I find the source code?

You can find the source code on GitHub using the link provided at the top of the page.

Related Guides

SKILL.md Source

# AssemblyAI Local Dev Loop

## Overview
Set up a fast, reproducible local development workflow for AssemblyAI transcription and LeMUR projects with mocking, caching, and hot reload.

## Prerequisites
- Completed `assemblyai-install-auth` setup
- Node.js 18+ with npm/pnpm
- TypeScript project with `tsx` or `ts-node`

## Instructions

### Step 1: Project Structure

```
my-assemblyai-project/
├── src/
│   ├── assemblyai/
│   │   ├── client.ts       # Singleton client
│   │   ├── transcribe.ts   # Transcription helpers
│   │   └── lemur.ts        # LeMUR helpers
│   └── index.ts
├── tests/
│   ├── transcribe.test.ts
│   └── fixtures/
│       └── sample-transcript.json  # Cached API response
├── .env.local              # Local secrets (git-ignored)
├── .env.example            # Template for team
└── package.json
```

### Step 2: Dev Scripts

```json
{
  "scripts": {
    "dev": "tsx watch src/index.ts",
    "test": "vitest",
    "test:watch": "vitest --watch",
    "transcribe": "tsx src/assemblyai/transcribe.ts"
  },
  "devDependencies": {
    "tsx": "^4.7.0",
    "vitest": "^1.6.0",
    "dotenv": "^16.4.0"
  },
  "dependencies": {
    "assemblyai": "^4.8.0"
  }
}
```

### Step 3: Singleton Client with Env Loading

```typescript
// src/assemblyai/client.ts
import 'dotenv/config';
import { AssemblyAI } from 'assemblyai';

let instance: AssemblyAI | null = null;

export function getClient(): AssemblyAI {
  if (!instance) {
    if (!process.env.ASSEMBLYAI_API_KEY) {
      throw new Error('ASSEMBLYAI_API_KEY not set. Copy .env.example to .env.local');
    }
    instance = new AssemblyAI({
      apiKey: process.env.ASSEMBLYAI_API_KEY,
    });
  }
  return instance;
}
```

### Step 4: Cache Transcription Results for Fast Iteration

```typescript
// src/assemblyai/transcribe.ts
import fs from 'fs';
import path from 'path';
import { getClient } from './client';
import type { Transcript } from 'assemblyai';

const CACHE_DIR = path.join(process.cwd(), '.assemblyai-cache');

export async function transcribeWithCache(
  audioUrl: string,
  options: Record<string, any> = {}
): Promise<Transcript> {
  const cacheKey = Buffer.from(audioUrl + JSON.stringify(options))
    .toString('base64url')
    .slice(0, 32);
  const cachePath = path.join(CACHE_DIR, `${cacheKey}.json`);

  // Return cached result in dev
  if (process.env.NODE_ENV !== 'production' && fs.existsSync(cachePath)) {
    console.log('[dev] Using cached transcript:', cacheKey);
    return JSON.parse(fs.readFileSync(cachePath, 'utf-8'));
  }

  const client = getClient();
  const transcript = await client.transcripts.transcribe({
    audio: audioUrl,
    ...options,
  });

  // Cache for next run
  fs.mkdirSync(CACHE_DIR, { recursive: true });
  fs.writeFileSync(cachePath, JSON.stringify(transcript, null, 2));
  console.log('[dev] Cached transcript:', cacheKey);

  return transcript;
}
```

### Step 5: Test with Mocked Responses

```typescript
// tests/transcribe.test.ts
import { describe, it, expect, vi, beforeEach } from 'vitest';
import { AssemblyAI } from 'assemblyai';

// Mock the assemblyai module
vi.mock('assemblyai', () => ({
  AssemblyAI: vi.fn().mockImplementation(() => ({
    transcripts: {
      transcribe: vi.fn().mockResolvedValue({
        id: 'test-transcript-id',
        status: 'completed',
        text: 'This is a test transcript.',
        audio_duration: 30,
        words: [
          { text: 'This', start: 0, end: 200, confidence: 0.99 },
          { text: 'is', start: 210, end: 350, confidence: 0.98 },
        ],
      }),
      get: vi.fn(),
      list: vi.fn(),
    },
    lemur: {
      task: vi.fn().mockResolvedValue({
        request_id: 'test-lemur-id',
        response: 'Test summary of the audio.',
      }),
    },
  })),
}));

describe('Transcription', () => {
  it('should transcribe audio and return text', async () => {
    const client = new AssemblyAI({ apiKey: 'test-key' });
    const result = await client.transcripts.transcribe({
      audio: 'https://example.com/audio.wav',
    });

    expect(result.status).toBe('completed');
    expect(result.text).toContain('test transcript');
    expect(result.words).toHaveLength(2);
  });

  it('should run LeMUR task on transcript', async () => {
    const client = new AssemblyAI({ apiKey: 'test-key' });
    const { response } = await client.lemur.task({
      transcript_ids: ['test-transcript-id'],
      prompt: 'Summarize this.',
    });

    expect(response).toContain('summary');
  });
});
```

## Output
- Hot-reloading dev server with `tsx watch`
- Cached transcription results to avoid repeated API calls during dev
- Mocked test suite that runs without API credentials
- Environment variable management with `.env.local`

## Error Handling
| Error | Cause | Solution |
|-------|-------|----------|
| `ASSEMBLYAI_API_KEY not set` | Missing env file | Copy `.env.example` to `.env.local` |
| `Module not found: assemblyai` | Missing dependency | Run `npm install assemblyai` |
| Stale cache results | Outdated cache | Delete `.assemblyai-cache/` directory |
| Test timeout | Slow mock setup | Ensure mocks resolve synchronously |

## Resources
- [AssemblyAI Node SDK](https://github.com/AssemblyAI/assemblyai-node-sdk)
- [Vitest Documentation](https://vitest.dev/)
- [tsx Documentation](https://github.com/privatenumber/tsx)

## Next Steps
See `assemblyai-sdk-patterns` for production-ready code patterns.

Related Skills

workhuman-local-dev-loop

1868
from jeremylongshore/claude-code-plugins-plus-skills

Workhuman local dev loop for employee recognition and rewards API. Use when integrating Workhuman Social Recognition, or building recognition workflows with HRIS systems. Trigger: "workhuman local dev loop".

wispr-local-dev-loop

1868
from jeremylongshore/claude-code-plugins-plus-skills

Wispr Flow local dev loop for voice-to-text API integration. Use when integrating Wispr Flow dictation, WebSocket streaming, or building voice-powered applications. Trigger: "wispr local dev loop".

windsurf-local-dev-loop

1868
from jeremylongshore/claude-code-plugins-plus-skills

Configure Windsurf local development workflow with Cascade, Previews, and terminal integration. Use when setting up a development environment, configuring Turbo mode, or establishing a fast iteration cycle with Windsurf AI. Trigger with phrases like "windsurf dev setup", "windsurf local development", "windsurf dev environment", "windsurf workflow", "develop with windsurf".

webflow-local-dev-loop

1868
from jeremylongshore/claude-code-plugins-plus-skills

Configure a Webflow local development workflow with TypeScript, hot reload, mocked API tests, and webhook tunneling via ngrok. Use when setting up a development environment, configuring test workflows, or establishing a fast iteration cycle with the Webflow Data API. Trigger with phrases like "webflow dev setup", "webflow local development", "webflow dev environment", "develop with webflow".

vercel-local-dev-loop

1868
from jeremylongshore/claude-code-plugins-plus-skills

Configure Vercel local development with vercel dev, environment variables, and hot reload. Use when setting up a development environment, testing serverless functions locally, or establishing a fast iteration cycle with Vercel. Trigger with phrases like "vercel dev setup", "vercel local development", "vercel dev environment", "develop with vercel locally".

veeva-local-dev-loop

1868
from jeremylongshore/claude-code-plugins-plus-skills

Veeva Vault local dev loop for REST API and clinical operations. Use when working with Veeva Vault document management and CRM. Trigger: "veeva local dev loop".

vastai-local-dev-loop

1868
from jeremylongshore/claude-code-plugins-plus-skills

Configure Vast.ai local development with testing and fast iteration. Use when setting up a development environment, testing instance provisioning, or building a fast iteration cycle for GPU workloads. Trigger with phrases like "vastai dev setup", "vastai local development", "vastai dev environment", "develop with vastai".

twinmind-local-dev-loop

1868
from jeremylongshore/claude-code-plugins-plus-skills

Set up local development workflow with TwinMind API integration. Use when building applications that integrate TwinMind transcription, testing API calls locally, or developing meeting automation tools. Trigger with phrases like "twinmind dev setup", "twinmind local development", "twinmind API testing", "build with twinmind".

together-local-dev-loop

1868
from jeremylongshore/claude-code-plugins-plus-skills

Together AI local dev loop for inference, fine-tuning, and model deployment. Use when working with Together AI's OpenAI-compatible API. Trigger: "together local dev loop".

techsmith-local-dev-loop

1868
from jeremylongshore/claude-code-plugins-plus-skills

TechSmith local dev loop for Snagit COM API and Camtasia automation. Use when working with TechSmith screen capture and video editing automation. Trigger: "techsmith local dev loop".

supabase-local-dev-loop

1868
from jeremylongshore/claude-code-plugins-plus-skills

Configure Supabase local development with the CLI, Docker, and migration workflow. Use when initializing a Supabase project locally, starting the local stack, writing migrations, seeding data, or iterating on schema changes. Trigger with phrases like "supabase local dev", "supabase start", "supabase init", "supabase db reset", "supabase local setup".

stackblitz-local-dev-loop

1868
from jeremylongshore/claude-code-plugins-plus-skills

Configure local development for WebContainer applications with hot reload and testing. Use when building browser-based IDEs, testing WebContainer file operations, or setting up development workflows for WebContainer projects. Trigger: "stackblitz dev setup", "webcontainer local", "test webcontainers locally".