meeting-transcription

Transcribe meeting audio with WhisperX and organize timestamped transcripts into Obsidian vault folders.

Updated Jan 24, 2026

Search Tags:#transcription #obsidian #meeting notes #audio processing #whisperx #speaker diarization

Ready to run

npx skills add https://github.com/Albatross679/snake-hrl-torchrl --skill meeting-transcription

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: meeting-transcription
Source: https://github.com/Albatross679/snake-hrl-torchrl/tree/main/skills/meeting-transcription
Command: npx skills add https://github.com/Albatross679/snake-hrl-torchrl --skill meeting-transcription

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires whisperx, ffmpeg, pyannote, and includes scripts (resource) and references (resource) components.

What problem does it solve?

This Skill automates the transcription of meeting audio, including speaker diarization, and organizes the output into structured notes within an Obsidian vault.

Core Features & Use Cases

Accurate Transcription: Leverages WhisperX for high-quality speech-to-text conversion.
Speaker Diarization: Identifies and labels different speakers in the audio.
Automated Note Creation: Generates organized meeting folders with transcripts and main notes.
Use Case: Transcribe a recorded client call, automatically identify who said what, and create a meeting note with a timestamped transcript for easy review and action item tracking.

Quick Start

Use the meeting-transcription skill to transcribe the audio file 'meeting_recording.m4a' with the topic 'Project Kickoff'.

Frequently Asked Questions about meeting-transcription

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

FAQPage Schema

How do I transcribe meeting audio with speaker diarization into Obsidian?▼

Meeting audio transcription into Obsidian is handled by WhisperX, which identifies different speakers and organizes the output into structured meeting folders with timestamped transcripts within your vault.

Do I need a HuggingFace token to use WhisperX for speaker diarization?▼

Yes, a HuggingFace token is required for speaker diarization. The transcription process relies on pyannote through WhisperX to identify and label different speakers in the meeting audio.

What dependencies are required for automated meeting note creation from audio files?▼

Automated meeting note creation requires Python, WhisperX, ffmpeg, and a HuggingFace token. These dependencies enable speech-to-text conversion, audio processing, and speaker labeling for the final notes.

How does WhisperX generate timestamped transcripts for meeting recordings?▼

WhisperX generates timestamped transcripts by processing meeting audio files and converting the speech into text with time markers. The transcribed content is then organized into main meeting notes within an Obsidian vault.

Can I use ffmpeg with WhisperX to transcribe m4a client calls?▼

Yes, you can transcribe m4a client calls using WhisperX and ffmpeg. The skill processes the audio file, identifies speakers through diarization, and creates a structured note with a timestamped transcript for review.