Setup & Installation
Or with the ClawHub CLI, for registry-managed skill folders outside a full OpenClaw workspace:
Version History
- Migrated documentation from JavaScript SDK usage to new Deepgram CLI tool. - Updated installation and authentication instructions for CLI workflow. - Provided new command examples for transcribing local files, URLs, microphone input, and STDIN. - Added guidance on output handling, transcript formats, and common CLI flags. - Revised workflow and skill summary to emphasize command-line usage and scripting capabilities.
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
Here's how your AI assistant might use this skill in practice.
User asks: transcribe interview.wav with speaker labels and save as text
- 1Run `deepgram login` to authenticate with stored API key
- 2Run `deepgram listen prerecorded interview.wav --model nova-2 --punctuate --diarize --format text`
- 3Redirect output to `transcript.txt`
Plain text transcript with speaker-separated lines saved to transcript.txt
Requirements
Accounts, API keys, or tools you or your AI assistant may need to set up while using this skill.