Gettr Transcribe & Summarize (MLX Whisper) for Openclaw

A local AI workflow for converting GETTR video content into searchable transcripts and structured Markdown summaries.

kevin37li
v1.0.4
Jan 29, 2026
0
0
0

Install & Download

1. ClawHub CLI

The fastest way to install a skill directly from the registry.

npx clawhub@latest install gettr-transcribe-summarize

2. Manual Installation

Copy the skill folder to one of these locations

Global
~/.openclaw/skills/
Workspace
<project>/skills/

Priority: Workspace > Local > Bundled

3. Prompt Installation

Copy this prompt to OpenClaw to install it automatically.

Help me install gettr-transcribe-summarize 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 Gettr Transcribe & Summarize (MLX Whisper)?

This skill provides a high-performance bridge between GETTR social media content and actionable text data. By leveraging MLX Whisper, it performs lightning-fast local transcription on Apple Silicon hardware, ensuring user privacy and eliminating cloud processing costs. As part of the Openclaw Skills ecosystem, it automates the complex process of extracting media URLs from both static posts and dynamic livestreams.

The tool is designed for users who need to digest long-form video content quickly. It transforms raw audio into formatted transcripts and summaries, supporting multiple languages and various output lengths. Whether you are a researcher, journalist, or casual user, this skill streamlines the consumption of social media broadcasts by providing structured, timestamped documentation.

Gettr Transcribe & Summarize (MLX Whisper) Use Cases

  • Creating text archives of GETTR livestreams for journalistic research.
  • Generating quick summaries of political commentary videos to save time.
  • Building timestamped outlines for long-form social media broadcasts to improve navigation.
  • Transcribing non-English GETTR content by utilizing specific language codes during the pipeline execution.

How Gettr Transcribe & Summarize (MLX Whisper) Works

  1. The user provides a GETTR URL, which the skill parses to identify the unique content slug.
  2. The skill extracts the direct video or HLS stream URL using a dedicated Python script or browser automation for signed URLs.
  3. FFmpeg downloads the source media and converts the audio track into a 16kHz mono WAV file.
  4. MLX Whisper processes the local audio file to generate a highly accurate VTT transcript with embedded timestamps.
  5. The transcript is analyzed and synthesized into a Markdown summary based on the user's preferred detail level (Short, Medium, or Detailed).

Gettr Transcribe & Summarize (MLX Whisper) Setup

To use this within your Openclaw Skills environment, ensure you have the necessary dependencies installed on your Apple Silicon Mac:

# Install FFmpeg via Homebrew
brew install ffmpeg

# Install MLX Whisper via Pip
pip install mlx-whisper

Once installed, you can trigger the pipeline manually or via an agent using the provided bash scripts.

Gettr Transcribe & Summarize (MLX Whisper) Data Schema & Taxonomy

The skill maintains a clean output hierarchy for every processed video, ensuring that data is organized by its unique GETTR slug:

File Name Format Description
audio.wav Audio (WAV) The extracted 16kHz mono audio source.
audio.vtt Text (VTT) The raw transcript including WebVTT timestamps.
summary.md Markdown The final deliverable containing bullets and/or a timestamped outline.

Gettr Transcribe & Summarize (MLX Whisper) Advanced Features

  • Local MLX Whisper execution optimized for Apple Silicon performance.
  • Support for explicit language flags (e.g., --language zh) to handle non-English content effectively.
  • Dynamic signed URL handling via browser automation to bypass HTTP 412 errors on streaming content.
  • Flexible output formatting allowing users to choose between simple bullet points or comprehensive timestamped outlines.
  • Built-in error handling with exponential backoff for robust network extraction.

SKILL.md


Loading

Related Openclaw Skills

Featured*