Agent skill · software engineering · jeremylongshore
deepgram-hello-world
Create a minimal working Deepgram transcription example.
Why this skill is useful
Provides specific Deepgram API usage patterns and examples for transcription that the AI wouldn't reliably generate on its own.
What it needs
Requires @deepgram/sdk installed locally. Requires deepgram account access. About 3k tokens when loaded. Last updated 2026-08-07. 2,604 stars on the source repository.
What this skill does
Deepgram Hello World Examples Transcribe a short licensed fixture in the development project, verify the response shape and selected model/language, and remove the fixture according to the test policy. Keep only a correlation ID and aggregate result in logs; do not use a customer call or retain its transcript as a tutorial artifact. Overview Minimal working examples for Deepgram speech-to-text. Transcribe an audio URL in 5 lines with createClient + listen.prerecorded.transcribeUrl. Includes local file transcription, Python equivalent, and Nova-3 model selection. Prerequisites npm install @deepgram/sdk completed DEEPGRAMAPIKEY environment variable set Audio source: URL or local file (WAV, MP3, FLAC, OGG, M4A) Instructions Step 1: Transcribe Audio from URL (TypeScript) Step 2: Transcribe a Local File Step 3: Python Equivalent Step 4: Add Features Step 5: Explore Model Options Model Use Case Speed Accuracy ------- ---------- ------- ---------- nova-3 General — best accuracy Fast Highest nova-2 General — proven stable Fast Very High nova-2-meeting Conference rooms, multiple speakers Fast High nova-2-phonecall Low-bandwidth phone audio Fast High base Cost-sensitive, high-volume Fastest Good whisper-large Multilingual (100+ languages) Slow High Step 6: Run It Output Working transcription from URL or local file Printed transcript text with confidence score Optional: speaker-labeled utterances Error Handling Error Cause Solution ------- ------- ---------- 401 Unauthorized Invalid API key Check DEEPGRAMAPIKEY 400 Bad Request Unsupported audio format Use WAV, MP3, FLAC, OGG, or M4A Empty transcript No speech in audio Verify audio has audible speech ENOTFOUND URL not reachable Check audio URL is publicly accessible Cannot find module '@deepgram/sdk' SDK not installed Run npm install @deepgram/sdk Resources Pre-recorded Audio Guide Model Options Smart Formatting Sample Audio Files Next Steps Proceed to deepgram-core-workflow-a for production transcription patterns or deepgram-c …
How to use it
Reference it in AdaL, Claude Code, Cursor or any coding agent — nothing to install:
@skills jeremylongshore/deepgram-hello-world