Skill

transcribe-md

Records microphone and system audio, transcribes to timestamped Markdown with speaker labels using whisper.cpp and Metal acceleration on macOS 14+. For meetings, notes, dictation.

Bash

Swift

Markdown

cli-tools

ai-ml

npx claudepluginhub hrescak/transcribe-md

Tool Access

This skill is limited to using the following tools:

Bash

Preview

Record and transcribe audio to a timestamped markdown file using whisper.cpp with Metal acceleration. Captures both microphone and system audio (via ScreenCaptureKit).

SKILL.md

Similar Skills

minutes-record

906

Records microphone audio from meetings/calls/voice memos, transcribes locally with whisper.cpp, saves timestamped markdown transcripts with summaries.

minutes

audio-transcriber

36.4k

Transcribes audio/video files to Markdown documentation with LLM summaries, speaker diarization, timestamps, metadata, and SRT/VTT subtitles using Faster-Whisper or Whisper.

6 files

antigravity-awesome-skills

audio-transcriber

Transcribes audio/video to Markdown docs with LLM summaries, speaker diarization, timestamps, metadata using Faster-Whisper/Whisper. For meetings, interviews, lectures.

8 files

claude-superskills

Stats

Stars92

Forks5

Last CommitMar 20, 2026

Actions

View Source View Plugin View on GitHub View README

Help us improve

Share bugs, ideas, or general feedback.

Transcribe to Markdown

Record and transcribe audio to a timestamped markdown file using whisper.cpp with Metal acceleration. Captures both microphone and system audio (via ScreenCaptureKit).

Usage

~/.local/share/transcribe-md/scripts/transcribe-to-md <file.md> ~/.local/share/transcribe-md/scripts/transcribe-to-md --duration 30 meeting.md ~/.local/share/transcribe-md/scripts/transcribe-to-md --mic-only notes.md

Parameters

$ARGUMENTS — Output file path and optional flags

--duration <MIN> — Auto-stop after this many minutes (e.g., --duration 30 for a 30-min meeting)

--mic-only — Skip system audio capture (mic only)

--devices — List available microphone devices

--mic <IDX> — Use a specific microphone by device index

--chunk <SEC> — Chunk duration in seconds (default: 10)

--setup — Install/verify dependencies without recording

Examples

/transcribe-md --duration 30 meeting.md — Record a 30-minute meeting

/transcribe-md notes.md — Record until Ctrl-C

/transcribe-md --mic-only dictation.md — Mic only, no system audio

/transcribe-md --devices — List available microphones

/transcribe-md — Ask what to transcribe, suggest a filename, ask if they want a time limit

How it works

Records mic via ffmpeg and system audio via a Swift helper (ScreenCaptureKit)

Transcribes in real-time using whisper.cpp with Metal GPU acceleration

Mic echoes of system audio are automatically deduplicated

Output: **[HH:MM:SS] You:** text and **[HH:MM:SS] Them:** text

Dependencies

Auto-installed on first run. whisper.cpp and model cached in ~/.cache/transcribe-cli/. System audio requires macOS 14+ and Screen Recording permission for the terminal.

Transcribe to Markdown

Record and transcribe audio to a timestamped markdown file using whisper.cpp with Metal acceleration. Captures both microphone and system audio (via ScreenCaptureKit).

Usage

~/.local/share/transcribe-md/scripts/transcribe-to-md <file.md>
~/.local/share/transcribe-md/scripts/transcribe-to-md --duration 30 meeting.md
~/.local/share/transcribe-md/scripts/transcribe-to-md --mic-only notes.md

Parameters

$ARGUMENTS — Output file path and optional flags
--duration <MIN> — Auto-stop after this many minutes (e.g., --duration 30 for a 30-min meeting)
--mic-only — Skip system audio capture (mic only)
--devices — List available microphone devices
--mic <IDX> — Use a specific microphone by device index
--chunk <SEC> — Chunk duration in seconds (default: 10)
--setup — Install/verify dependencies without recording

Examples

/transcribe-md --duration 30 meeting.md — Record a 30-minute meeting
/transcribe-md notes.md — Record until Ctrl-C
/transcribe-md --mic-only dictation.md — Mic only, no system audio
/transcribe-md --devices — List available microphones
/transcribe-md — Ask what to transcribe, suggest a filename, ask if they want a time limit

How it works

Records mic via ffmpeg and system audio via a Swift helper (ScreenCaptureKit)
Transcribes in real-time using whisper.cpp with Metal GPU acceleration
Mic echoes of system audio are automatically deduplicated
Output: **[HH:MM:SS] You:** text and **[HH:MM:SS] Them:** text

Dependencies

Auto-installed on first run. whisper.cpp and model cached in ~/.cache/transcribe-cli/. System audio requires macOS 14+ and Screen Recording permission for the terminal.