transcription-helper

Transcribe local videos and YouTube content into timestamped transcripts using gpt-4o-transcribe.

4|Updated Nov 29, 2025

Search Tags:#video #transcription #audio #knowledge-graph #gpt-4o-transcribe

One-click install

npx skills add https://github.com/costiash/CognivAgent --skill transcription-helper

Or copy as Structured Prompt for Agent▼

Please help me install this Agent Skill.
Skill: transcription-helper
Source: https://github.com/costiash/CognivAgent/tree/main/app/agent/resources/.claude/skills/transcription-helper
Command: npx skills add https://github.com/costiash/CognivAgent --skill transcription-helper

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill guides users through the end-to-end transcription workflow, turning local videos and YouTube content into accurate transcripts for downstream analysis and knowledge extraction.

Core Features & Use Cases

Input gathering: Collects video source, language, and domain vocabulary to improve transcription accuracy.
Transcription: Uses gpt-4o-transcribe to convert audio/video content into transcripts with timestamps.
Workflow orchestration: Manages the lifecycle from input gathering to results, including job IDs and progress updates.
Use Case: Transcribe a lecture video and obtain a searchable transcript with word-level timestamps for later KG extraction.

Quick Start

Run the transcription helper with a video file path (e.g., /videos/lecture.mp4) and optional language code (e.g., en). The skill will initiate Phase 1, create a background transcription job, and present results upon completion.