gastrohem-media-processor
CommunityTranscribe audio, OCR images, fast and smart.
AuthorasapMaki
Version1.0.0
Installs0
System Documentation
What problem does it solve?
Manually transcribing audio and extracting information from images in daily WhatsApp folders is a slow and labor-intensive process. This skill automates media processing, saving significant time and ensuring no critical information is missed from your daily communications.
Core Features & Use Cases
- Parallel Audio Transcription: Transcribes audio files (
.mp3,.ogg, etc.) in parallel usinginsanely-fast-whisper, generating.jsonoutputs for easy integration. - Intelligent Image OCR: Uses Claude's vision capabilities to perform OCR on images, creating natural language
.mdsummaries focused on Gastrohem-relevant information. - Use Case: At the end of the day, run this skill to automatically process all voice notes and images from your team's WhatsApp conversations, getting structured text summaries ready for review and further action.
Quick Start
To process all media for today, simply ask: Process media. To process media for a specific date (e.g., 24.10), ask: Process media for 24.10.
Dependency Matrix
Required Modules
insanely-fast-whisper
Components
scripts
💻 Claude Code Installation
Recommended: Let Claude install automatically. Simply copy and paste the text below to Claude Code.
Please help me install this Skill: Name: gastrohem-media-processor Download link: https://github.com/asapMaki/vozzy-whatsapp/archive/main.zip#gastrohem-media-processor Please download this .zip file, extract it, and install it in the .claude/skills/ directory.
Agent Skills Search Helper
Install a tiny helper to your Agent, search and equip skill from 223,000+ vetted skills library on demand.