Can it identify different speakers in a recording?

Yes, the skill supports speaker diarization to distinguish between participants, making it highly effective for interviews and multi-person meetings.

How does it generate the meeting summaries?

After the audio is transcribed locally, the text can be processed through an LLM (like Claude) using specialized prompts to extract topics, decisions, and action items.

Do I need a paid API for transcription?

No, this skill primarily uses local engines like Faster-Whisper or OpenAI Whisper, allowing for free and private transcription on your own hardware.

Which audio formats are supported by this skill?

The skill supports common formats including MP3, WAV, M4A, OGG, FLAC, WEBM, and MP4. If ffmpeg is installed, it can automatically convert unsupported formats.

Is my audio data kept private?

Yes, because the transcription engine runs locally on your machine, your raw audio data is not sent to external APIs for the speech-to-text process.

Audio Transcriber & Meeting Assistant

Name: Audio Transcriber & Meeting Assistant
Author: sickn33

bysickn33

•

31,722

•

Productivity & Workflow

Converts audio recordings into professional Markdown documentation with intelligent meeting minutes and executive summaries.

The audio-transcriber skill automates the transformation of raw audio and video files into structured, actionable Markdown documentation. By leveraging high-performance engines like Faster-Whisper and integrating with LLMs for summarization, it extracts technical metadata, identifies speakers, and generates comprehensive meeting minutes including decisions and action items. This skill is designed for zero-configuration use, automatically detecting local tools and handling various audio formats like MP3, WAV, and M4A, making it ideal for developers and project managers who need to document meetings, interviews, or lectures without manual effort.

Key Features

01Multi-speaker identification and timestamped dialogue tracking

02Comprehensive metadata extraction including duration, language, and file stats

03Automated generation of meeting minutes with topics, decisions, and tasks

0431,722 GitHub stars

05High-speed local transcription using Faster-Whisper and OpenAI Whisper

06Automatic audio format conversion using ffmpeg integration

Use Cases

01Transcribing and summarizing technical interviews or research sessions

02Generating professional documentation and action items from recorded team meetings

03Creating searchable Markdown archives and subtitles for video content

What are Skills?·How to Install

Install with 🐟 Skill.Fish

npx skillfish add sickn33/antigravity-awesome-skills audio-transcriber

For use in Claude.ai and ChatGPT

Key Features

01Multi-speaker identification and timestamped dialogue tracking

02Comprehensive metadata extraction including duration, language, and file stats

03Automated generation of meeting minutes with topics, decisions, and tasks

0431,722 GitHub stars

05High-speed local transcription using Faster-Whisper and OpenAI Whisper

06Automatic audio format conversion using ffmpeg integration

Use Cases

01Transcribing and summarizing technical interviews or research sessions

02Generating professional documentation and action items from recorded team meetings

03Creating searchable Markdown archives and subtitles for video content

What are Skills?·How to Install

Install with 🐟 Skill.Fish

npx skillfish add sickn33/antigravity-awesome-skills audio-transcriber

For use in Claude.ai and ChatGPT