tool-transcribe-social

Extract and transcribe audio from social media URLs using yt-dlp and Groq Whisper.

20|15|Updated May 7, 2026
One-click install
npx skills add https://github.com/iamasters-academy/iamasters-os --skill tool-transcribe-social
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: tool-transcribe-social
Source: https://github.com/iamasters-academy/iamasters-os/tree/main/skills-library/tools/tool-transcribe-social
Command: npx skills add https://github.com/iamasters-academy/iamasters-os --skill tool-transcribe-social

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires python3, yt-dlp, ffmpeg, requests, instaloader, and includes scripts (resource) and assets (resource) components.

What problem does it solve?

This Skill addresses the challenge of manually transcribing audio from social media videos, enabling efficient analysis of content without the time-consuming task of manual transcription.

Core Features & Use Cases

  • Social Media Audio Download & Transcription: Extracts audio from Instagram Reels, TikTok videos, YouTube Shorts, and other supported URLs, then transcribes it using Groq Whisper.
  • Instagram Metadata Extraction: Optionally retrieves caption, hashtags, mentions, and public comments from Instagram posts.
  • Use Case: For example, quickly analyzing customer feedback from a social media video for sentiment analysis or keyword extraction.

Quick Start

Execute the 'tool-transcribe-social' command followed by the URL of the social media content you want to transcribe.

Frequently Asked Questions about tool-transcribe-social

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

FAQPage Schema
How do I transcribe audio from social media videos like Instagram Reels and TikTok?

Social media audio transcription extracts spoken words from video formats like Instagram Reels and TikTok. It works by downloading the audio track via yt-dlp, then passing it through Groq Whisper to generate accurate text output for content analysis.

Do I need Python and ffmpeg to extract audio from YouTube Shorts?

Yes, Python, yt-dlp, and ffmpeg are required dependencies to extract and transcribe YouTube Shorts. They manage the underlying video downloading and audio conversion processes before Groq Whisper generates the text transcript.

Can I extract captions and hashtags along with the audio transcription from Instagram posts?

Yes, you can extract Instagram metadata including captions, hashtags, mentions, and public comments alongside the audio transcription. This requires the optional instaloader dependency to gather the complete post data for research.

What is the best way to automate social listening for TikTok video content?

Automating social listening for TikTok involves batch processing video URLs through an automated transcription pipeline. Passing URLs to yt-dlp for audio extraction and Groq Whisper for transcription generates structured text for keyword analysis.

Does yt-dlp support downloading audio from multiple social media platforms?

Yes, yt-dlp supports downloading audio from various social media platforms including YouTube, Instagram, and TikTok. It extracts audio streams from supported URLs before Groq Whisper handles the voice transcription process.