LLM Transcription Skill

Convert images and audio files into markdown text using LLMs.

2|Updated May 17, 2025

Search Tags:#ocr #markdown #transcription #audio processing #speech to text #image to text

Ready to run

npx skills add https://github.com/karstenheld3/OpenAI-BackendTools --skill llm-transcription-skill

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: LLM Transcription Skill
Source: https://github.com/karstenheld3/OpenAI-BackendTools/tree/main/.windsurf/skills/llm-transcription
Command: npx skills add https://github.com/karstenheld3/OpenAI-BackendTools --skill llm-transcription-skill

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires openai, anthropic, httpx, and includes scripts (resource) and references (resource) components.

What problem does it solve?

This Skill automates the conversion of visual and audio information into structured text, making it easily searchable, editable, and usable in downstream applications.

Core Features & Use Cases

Image to Markdown: Converts screenshots, documents, and diagrams into formatted Markdown text, preserving structure and extracting data from graphics.
Audio to Markdown: Transcribes audio files (meetings, lectures, interviews) into readable Markdown text, including speaker identification and formatting.
Batch Processing: Handles multiple files efficiently for large-scale transcription needs.
Use Case: Transcribe a scanned PDF document into editable Markdown for easy content reuse, or convert a recorded meeting into a searchable transcript with clear section breaks.

Quick Start

Use the LLM Transcription Skill to transcribe the audio file 'meeting_recording.mp3' into a markdown file named 'meeting_transcript.md'.

Frequently Asked Questions about LLM Transcription Skill

High-intent search queries and answers about installing and using this skill.

FAQPage Schema

How do I transcribe audio files to markdown with speaker identification?▼

Audio to markdown transcription converts recorded meetings into structured text using the Whisper API, including speaker identification and clear section breaks. It processes audio files like interviews or lectures into searchable, editable markdown documents.

What is the best way to convert images and screenshots to markdown text?▼

Converting images to markdown uses ensemble, judge, and refinement steps to extract text from screenshots and diagrams while preserving structure. This approach ensures formatted markdown output that maintains the original document layout and graphical data.

Does this transcription tool support batch processing for multiple audio and image files?▼

Batch processing handles multiple files efficiently for large-scale audio and image transcription needs. It converts bulk visual and audio information into structured markdown text, making the content searchable and usable in downstream applications.

Can I use OpenAI and Anthropic models for image to text conversion?▼

Image to text conversion supports multiple models from both OpenAI and Anthropic. This multi-model support allows flexible LLM selection during the ensemble, judge, and refinement phases to optimize markdown extraction from documents and graphics.

How do I transcribe a scanned PDF document into editable markdown?▼

Transcribing a scanned PDF involves image-to-markdown conversion that preserves document structure and extracts data from embedded graphics. The process uses ensemble steps and judge logic to output reusable, formatted markdown text.

Why use LLMs for speech to text instead of standard optical character recognition?▼

Using LLMs for transcription goes beyond standard OCR by preserving document structure and extracting data from graphics. The ensemble and refinement steps format the extracted content directly into markdown, providing searchable and editable text for downstream use.