Automate WhatsApp media processing with audio transcription and image OCR.
npx skills add https://github.com/asapMaki/vozzy-whatsapp --skill media-workflow
Please help me install this Agent Skill. Skill: media-workflow Source: https://github.com/asapMaki/vozzy-whatsapp/tree/main/.claude/skills/media-workflow Command: npx skills add https://github.com/asapMaki/vozzy-whatsapp --skill media-workflow
Managing WhatsApp media involves multiple, disconnected steps: transcribing audio, OCRing images, and then integrating them into chat logs. This skill streamlines the entire process into a single, automated workflow, eliminating manual coordination and ensuring all media is processed and logged efficiently.
gastrohem-media-processor (audio transcription, image OCR) and chat-integrator (merging into chat.md) into one seamless command.chat.md files and providing a comprehensive report, all in one go.To run the complete media workflow for today, simply ask: Process and integrate media. To run the workflow for a specific date (e.g., 24.10), ask: Process and integrate media for 24.10.
High-intent search queries and answers about installing and using this skill.
Media workflow automates end-to-end WhatsApp processing by transcribing audio files and performing OCR on images in a single command, then integrating results into chat logs. It handles daily batch processing across departments with date-based or folder-based scopes, outputting transcriptions, image summaries, and updated chat.md files.
Yes, media workflow supports CLI options including --scan-date for specific dates and --folder to target particular directories. You can also use --dry-run to preview changes, --no-backup to skip backups, and --output-json to export results as JSON before updating chat records.
Media workflow transcribes voice notes using Whisper and extracts text from images via OCR, then automatically merges these results into your chat.md documentation. It produces JSON transcriptions and Markdown image summaries alongside updated chat records and backups.
Media workflow is designed for daily use to keep chat logs updated with newly processed media. Running it at the end of each day ensures all voice notes and images from that day are transcribed, OCR'd, and integrated into your chat.md files automatically.
Media workflow depends on insanely-fast-whisper for audio transcription. You need WhatsApp media files (audio and images) organized by date or folder, and existing chat.md files to merge processed content into.
Yes, media workflow supports daily batch processing across departments with configurable date-based or folder-based scopes. It orchestrates transcription and OCR across multiple media files and outputs comprehensive reports with transcriptions, summaries, and updated chat records in one execution.
asapMakiTranscribe audio files and OCR images from Gastrohem WhatsApp folders.
cofinGenerate project summary exports from flow definitions, patterns, and archives.
asapMakiInsert audio transcriptions and image summaries into chat.md chronologically.
astoreyaiCapture screen regions and convert OCR text to Markdown notes.