Audio Transcriber

Takes audio files and turns them into structured Markdown documentation with meeting minutes, action items, and executive summaries. It auto-detects whether you have Faster-Whisper or standard Whisper installed and offers one-click dependency setup if you don't. The workflow validates your audio file format, extracts metadata like duration and file size, runs transcription with speaker diarization, then uses LLM integration to pull out topics discussed, decisions made, and action items with timestamps. Output is professional Markdown with tables, checkboxes, and proper formatting. Works with MP3, WAV, M4A, and other common formats, converting on the fly if ffmpeg is available. Good for meeting recordings, interviews, or any audio you need turned into searchable, scannable text with intelligent structure rather than just a raw transcript dump.

skills.sh installs: 1.1K
GitHub stars: 43.1K
last updated: Jul 14, 2026

View on GitHub

Install

$ npx -y skills add sickn33/antigravity-awesome-skills --skill audio-transcriber --agent claude-code

Installs into .claude/skills of the current project.

Files

Detailed Guide

Read the detailed guide before executing this skill. It retains the complete procedure and reference material. Treat its safety, prerequisites, and validation requirements as mandatory. For focused work, load the relevant sections; for end-to-end work, read the guide completely.

When to Use

Invoke this skill when:

User needs to transcribe audio/video files to text
User wants meeting minutes automatically generated from recordings
User needs a transcript; explain that speaker diarization is not bundled
User needs source text for later subtitle preparation; SRT/VTT export requires a separate tool
User wants executive summaries of long audio content
User asks variations of "transcribe this audio", "convert audio to text", "generate meeting notes from recording"
User has audio files in common formats (MP3, WAV, M4A, OGG, FLAC, WEBM)

Examples

From the skill directory, with dependencies installed in the selected interpreter and an existing private output directory inside the current workspace:

python3 scripts/transcribe.py /path/to/meeting.mp3 --output-dir ./private-reports --llm none

SKILL.md on GitHub

Details

Repository: github.com/sickn33/antigravity-awesome-skills
First seen: Apr 16, 2026