skills.rest
coderfengyun
coderfengyunCOMMUNITY
Explore all skills by this author →
GitHub

transcribe

Transcribe audio and video into Markdown transcripts with Qwen3-ASR.

Updated Feb 26, 2026
Search Tags:#markdown#video#audio#podcast#transcribe#sources.jsonl
One-click install
npx skills add https://github.com/coderfengyun/digital-brain-of-me --skill transcribe-coderfengyun
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: transcribe
Source: https://github.com/coderfengyun/digital-brain-of-me/tree/main/.claude/skills/transcribe
Command: npx skills add https://github.com/coderfengyun/digital-brain-of-me --skill transcribe-coderfengyun

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Transcribing audio and video content manually is time-consuming and error-prone. This Skill automates audio/video transcription to produce searchable Markdown transcripts and preserves provenance by logging outputs in sources.jsonl.

Core Features & Use Cases

  • Audio/Video Transcription: Convert podcasts, lectures, and videos into readable text.
  • Multi-Input Support: Transcribe from local files or RSS/Spotify-based feeds and save outputs under the appropriate content category.
  • Output & Traceability: Generate Markdown transcripts and register entries in sources.jsonl for easy discovery and reuse.

Quick Start

Run the transcribe script with a local audio or video file to generate a Markdown transcript and register it in sources.jsonl.

Frequently Asked Questions about transcribe

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

FAQPage Schema
How do I transcribe a podcast from an RSS feed into Markdown?▼

Transcribe a podcast by processing RSS or Spotify feeds to generate per-episode Markdown transcripts. The tool automatically logs metadata for each episode into sources.jsonl for provenance and discovery.

What's the best way to convert local audio and video files to text?▼

Convert local audio and video files by running the transcription script, which outputs Markdown transcripts. It uses Qwen3-ASR with a whisper fallback to ensure accurate text conversion.

Do I need ffmpeg and Python to use this transcription tool?▼

Yes, you need ffmpeg for audio and video preprocessing, along with Python scripts and configured Qwen3-ASR or whisper-cpp models. This environment setup is required to run the transcription process.

Can I transcribe video content and apply speaker diarization?▼

Yes, video content transcription supports optional speaker diarization. It processes video files into readable Markdown transcripts using Qwen3-ASR or whisper-cpp models as fallback.

How does sources.jsonl track transcribed audio and video episodes?▼

sources.jsonl records metadata for each transcribed audio or video episode. This mechanism preserves provenance and ensures generated Markdown transcripts remain easily discoverable and reusable.

What languages are supported for audio transcription?▼

Audio transcription supports multiple languages through Qwen3-ASR and whisper-cpp models. Language support depends on the specific model configured in your environment for processing.

Related Skills

Explore More Content & Communication Skills→
hwj123hwjhwj123hwj
4

video-analyze

Extract frames from videos and transcribe audio with Whisper.

Community
Advanced
Jansen611Jansen611
2

youtube-transcript

Download YouTube video transcripts and convert VTT subtitles into timestamped Markdown.

Community
Intermediate
RimaginationRimagination
127

dy-note

Convert Douyin video and comment data into evidence-graded learning assets.

Community
Advanced
ruiyangruiyiruiyangruiyi

whisper

Transcribe spoken audio into timestamped text or English translations.

Community
Intermediate