deepgram
by nerkn
Speech & TranscriptionBrief
— command-line interface for Deepgram speech-to-text.
Description
What This Skill Does
Command-line interface for Deepgram speech-to-text. Transcribes local files, remote URLs, piped audio, or live microphone input. Outputs JSON, plain text, SRT, or VTT.
Pipe-friendly CLI design lets it slot into shell scripts and automation without any UI or SDK setup.
When to Use It
- Transcribe a recorded meeting to text
- Generate subtitles for a video file
- Dictate notes via microphone
- Pipe audio from a script into a transcript
- Separate speakers in an interview recording
Example Workflow
User asks: transcribe interview.wav with speaker labels and save as text
- 1
Run
deepgram loginto authenticate with stored API key - 2
Run
deepgram listen prerecorded interview.wav --model nova-2 --punctuate --diarize --format text - 3
Redirect output to
transcript.txt
Plain text transcript with speaker-separated lines saved to transcript.txt
Requirements
- Deepgram API key
- Deepgram account (deepgram.com)
Installation
clawhub install nerkn/deepgramRun the CLI command, or paste the prompt into Claude Code, Cursor, Codex or whichever coding agent you use.