deepgram-hello-world
Create a minimal working Deepgram transcription example.Use when starting a new Deepgram integration, testing your setup,or learning basic Deepgram API patterns.Trigger with phrases like "deepgram hello world", "deepgram example","deepgram quick start", "simple transcription", "transcribe audio".
When & Why to Use This Skill
This Claude skill provides a minimal, production-ready boilerplate for Deepgram's speech-to-text API integration. It enables developers to quickly implement audio transcription from both URLs and local files using TypeScript and Python, facilitating rapid prototyping, environment verification, and a smooth onboarding process for the Deepgram SDK.
Use Cases
- Rapid Prototyping: Quickly generate working scripts to test Deepgram's transcription accuracy and 'Nova-2' model performance on specific audio samples.
- Integration Onboarding: Provide a standardized 'Hello World' template for new developers to understand basic authentication, client initialization, and API patterns.
- Environment Verification: Troubleshoot API key configurations and network connectivity issues by running a minimal, known-good transcription script.
- Cross-Language Implementation: Access ready-to-use code snippets for both Python and TypeScript environments to ensure consistent API usage across different microservices.
| name | deepgram-hello-world |
|---|---|
| description | | |
| allowed-tools | Read, Write, Edit |
| version | 1.0.0 |
| license | MIT |
| author | Jeremy Longshore <jeremy@intentsolutions.io> |
Deepgram Hello World
Overview
Minimal working example demonstrating core Deepgram speech-to-text functionality.
Prerequisites
- Completed
deepgram-install-authsetup - Valid API credentials configured
- Audio file for transcription (or use URL)
Instructions
Step 1: Create Entry File
Create a new file for your hello world example.
Step 2: Import and Initialize Client
import { createClient } from '@deepgram/sdk';
const deepgram = createClient(process.env.DEEPGRAM_API_KEY);
Step 3: Transcribe Audio from URL
async function transcribe() {
const { result, error } = await deepgram.listen.prerecorded.transcribeUrl(
{ url: 'https://static.deepgram.com/examples/nasa-podcast.wav' },
{ model: 'nova-2', smart_format: true }
);
if (error) throw error;
console.log(result.results.channels[0].alternatives[0].transcript);
}
transcribe();
Output
- Working code file with Deepgram client initialization
- Successful transcription response
- Console output showing transcribed text
Error Handling
| Error | Cause | Solution |
|---|---|---|
| Import Error | SDK not installed | Verify with npm list @deepgram/sdk |
| Auth Error | Invalid credentials | Check environment variable is set |
| Audio Format Error | Unsupported format | Use WAV, MP3, FLAC, or OGG |
| URL Not Accessible | Cannot fetch audio | Ensure URL is publicly accessible |
Examples
TypeScript - Transcribe URL
import { createClient } from '@deepgram/sdk';
const deepgram = createClient(process.env.DEEPGRAM_API_KEY);
async function main() {
const { result, error } = await deepgram.listen.prerecorded.transcribeUrl(
{ url: 'https://static.deepgram.com/examples/nasa-podcast.wav' },
{ model: 'nova-2', smart_format: true }
);
if (error) throw error;
console.log('Transcript:', result.results.channels[0].alternatives[0].transcript);
}
main().catch(console.error);
TypeScript - Transcribe Local File
import { createClient } from '@deepgram/sdk';
import { readFileSync } from 'fs';
const deepgram = createClient(process.env.DEEPGRAM_API_KEY);
async function transcribeFile(filePath: string) {
const audio = readFileSync(filePath);
const { result, error } = await deepgram.listen.prerecorded.transcribeFile(
audio,
{ model: 'nova-2', smart_format: true, mimetype: 'audio/wav' }
);
if (error) throw error;
console.log('Transcript:', result.results.channels[0].alternatives[0].transcript);
}
transcribeFile('./audio.wav');
Python Example
from deepgram import DeepgramClient, PrerecordedOptions
import os
deepgram = DeepgramClient(os.environ.get('DEEPGRAM_API_KEY'))
options = PrerecordedOptions(
model="nova-2",
smart_format=True,
)
url = {"url": "https://static.deepgram.com/examples/nasa-podcast.wav"}
response = deepgram.listen.rest.v("1").transcribe_url(url, options)
print(response.results.channels[0].alternatives[0].transcript)
Resources
Next Steps
Proceed to deepgram-local-dev-loop for development workflow setup.