A powerful command-line interface for transcribing local audio files, remote URLs, and live microphone input using Deepgram's AI models.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install deepgram
2. Manual Installation
Copy the skill folder to one of these locations
~/.openclaw/skills/ <project>/skills/ Priority: Workspace > Local > Bundled
3. Prompt Installation
Copy this prompt to OpenClaw to install it automatically.
Help me install deepgram using Clawhub. If Clawhub is not installed, install it first (npm i -g clawhub).
Prefer to download?
Get the raw skill files in a ZIP archive.
What is Deepgram CLI Skill?
The Deepgram CLI Skill provides developers with a robust toolset for speech-to-text processing without the need for a complex graphical interface. It leverages world-class AI models like Nova-2 to deliver high-speed, accurate transcriptions directly within the terminal environment. This Openclaw Skills utility is engineered for high-throughput automation, allowing users to pipe audio data, handle remote streams, and generate industry-standard subtitle formats with minimal configuration.
Deepgram CLI Skill Use Cases
- Transcribing local audio files for content archival or indexing.
- Processing remote audio streams directly from URLs or public links.
- Capturing live microphone input for real-time dictation and logging.
- Generating SRT or VTT subtitle files for video production workflows.
- Automating transcription pipelines via shell scripts and system pipes.
How Deepgram CLI Skill Works
- Source audio data from a local file, a remote URL, or a live microphone stream.
- Execute the deepgram listen command while specifying required flags like model and language.
- Send the audio data to Deepgram's high-concurrency cloud infrastructure for processing.
- Receive the resulting transcription in a structured format such as JSON, text, or subtitles.
- Redirect or pipe the output to a destination file or another script for further automation.
Deepgram CLI Skill Setup
To get started with this skill, install the CLI tool and authenticate with your API key:
npm install -g @deepgram/cli
deepgram login
Deepgram CLI Skill Data Schema & Taxonomy
The skill outputs data in several formats to suit different technical requirements:
| Format | Description |
|---|---|
| JSON | Comprehensive data including timestamps, confidence scores, and word-level details. |
| Text | A clean, plain-text representation of the audio content. |
| SRT/VTT | Standardized subtitle formats for media players and video editors. |
| Metadata | Information regarding the model used, language detected, and diarization results. |
Deepgram CLI Skill Advanced Features
- Speaker Diarization: Identify and label different speakers within a single audio stream.
- STDIN Streaming: Use Unix pipes to stream raw audio data directly into the transcription engine.
- Punctuation & Formatting: Automatically add periods, commas, and casing to the generated text.
- Multi-Model Selection: Switch between various models like Nova-2 or General based on use-case requirements.
- High-Speed Processing: Optimized for fast-turnaround transcriptions within the Openclaw Skills ecosystem.
SKILL.md
Loading
Related Openclaw Skills
PR Risk Analyzer
Automatically evaluate GitHub pull requests for security vulnerabilities, exposed secrets, and structural merge risks.
Agent Voice
A command-line blogging and social platform designed specifically for AI agents to publish, share, and interact through markdown posts.
Prompt Library Curator
A professional utility for curating, organizing, and exporting multi-language prompt libraries across various industrial and creative categories.
Jira Admin Cloud
A comprehensive administrative playbook for Jira Cloud designed to streamline project management, JSM configuration, and Confluence integration.
NewsHelp Content Navigator
A navigation-first approach to accessing structured news data and global topic archives efficiently.
FTdesign HTML Generator
An automated interface builder that generates standardized HTML preview pages for lists, forms, and details using the FTdesign system.
Featured*
