From qe-framework
Transcribes audio files (MP3, WAV, M4A, etc.) to Markdown meeting minutes, subtitles, or summaries using Faster-Whisper or Whisper. Auto-detects tools, supports speaker diarization.
How this skill is triggered — by the user, by Claude, or both
Slash command
/qe-framework:Qaudio-transcriberThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
This skill automates audio-to-text transcription with professional Markdown output, extracting rich technical metadata (speakers, timestamps, language, file size, duration) and generating structured meeting minutes and executive summaries. It uses Faster-Whisper or Whisper with zero configuration, working universally across projects without hardcoded paths or API keys.
This skill automates audio-to-text transcription with professional Markdown output, extracting rich technical metadata (speakers, timestamps, language, file size, duration) and generating structured meeting minutes and executive summaries. It uses Faster-Whisper or Whisper with zero configuration, working universally across projects without hardcoded paths or API keys.
Inspired by tools like Plaud, this skill transforms raw audio recordings into actionable documentation, making it ideal for meetings, interviews, lectures, and content analysis.
Invoke this skill when:
Objective: Identify available transcription engines without user configuration.
Actions:
Run detection commands to find installed tools:
# Check for Faster-Whisper (preferred - 4-5x faster)
if python3 -c "import faster_whisper" 2>/dev/null; then
TRANSCRIBER="faster-whisper"
echo "✅ Faster-Whisper detected (optimized)"
# Fallback to original Whisper
elif python3 -c "import whisper" 2>/dev/null; then
TRANSCRIBER="whisper"
echo "✅ OpenAI Whisper detected"
else
TRANSCRIBER="none"
echo "⚠️ No transcription tool found"
fi
# Check for ffmpeg (audio format conversion)
if command -v ffmpeg &>/dev/null; then
echo "✅ ffmpeg available (format conversion enabled)"
else
echo "ℹ️ ffmpeg not found (limited format support)"
fi
If no transcriber found:
Offer automatic installation using the provided script:
echo "⚠️ No transcription tool found"
echo ""
echo "🔧 Auto-install dependencies? (Recommended)"
read -p "Run installation script? [Y/n]: " AUTO_INSTALL
if [[ ! "$AUTO_INSTALL" =~ ^[Nn] ]]; then
pip install faster-whisper
brew install ffmpeg # macOS
else
echo ""
echo "📦 Manual installation required:"
echo ""
echo "Recommended (fastest):"
echo " pip install faster-whisper"
echo ""
echo "Alternative (original):"
echo " pip install openai-whisper"
echo ""
echo "Optional (format conversion):"
echo " brew install ffmpeg # macOS"
echo " apt install ffmpeg # Linux"
echo ""
exit 1
fi
Objective: Verify file exists, check format, and extract metadata.
Actions:
Accept file path or URL from user:
meeting.mp3https://example.com/audio.mp3 (download to temp directory)Verify file exists:
if [[ ! -f "$AUDIO_FILE" ]]; then
echo "❌ File not found: $AUDIO_FILE"
exit 1
fi
FILE_SIZE=$(du -h "$AUDIO_FILE" | cut -f1)
DURATION=$(ffprobe -v error -show_entries format=duration \
-of default=noprint_wrappers=1:nokey=1 "$AUDIO_FILE" 2>/dev/null)
FORMAT=$(ffprobe -v error -select_streams a:0 -show_entries \
stream=codec_name -of default=noprint_wrappers=1:nokey=1 "$AUDIO_FILE" 2>/dev/null)
DURATION_HMS=$(date -u -r "$DURATION" +%H:%M:%S 2>/dev/null || echo "Unknown")
EXTENSION="${AUDIO_FILE##*.}"
SUPPORTED_FORMATS=("mp3" "wav" "m4a" "ogg" "flac" "webm" "mp4")
if [[ ! " ${SUPPORTED_FORMATS[@]} " =~ " ${EXTENSION,,} " ]]; then
echo "⚠️ Unsupported format: $EXTENSION"
if command -v ffmpeg &>/dev/null; then
echo "🔄 Converting to WAV..."
ffmpeg -i "$AUDIO_FILE" -ar 16000 "${AUDIO_FILE%.*}.wav" -y
AUDIO_FILE="${AUDIO_FILE%.*}.wav"
else
echo "❌ Install ffmpeg to convert formats: brew install ffmpeg"
exit 1
fi
fi
Transcribe using detected engine and generate structured Markdown output.
Objective: Create structured Markdown with metadata, transcription, meeting minutes, and summary.
Output Template:
# Audio Transcription Report
## 📊 Metadata
| Field | Value |
|-------|-------|
| **File Name** | {filename} |
| **File Size** | {file_size} |
| **Duration** | {duration_hms} |
| **Language** | {language} ({language_code}) |
| **Processed Date** | {process_date} |
| **Speakers Identified** | {num_speakers} |
| **Transcription Engine** | {engine} (model: {model}) |
## 📋 Meeting Minutes
### Participants
- {speaker_1}
- {speaker_2}
### Topics Discussed
1. **{topic_1}** ({timestamp})
- {key_point_1}
- {key_point_2}
### Decisions Made
- ✅ {decision_1}
- ✅ {decision_2}
### Action Items
- [ ] **{action_1}** - Assigned to: {speaker} - Due: {date_if_mentioned}
- [ ] **{action_2}** - Assigned to: {speaker}
*Generated by Qaudio-transcriber*
*Transcription engine: {engine} | Processing time: {elapsed_time}s*
TIMESTAMP=$(date +%Y%m%d-%H%M%S)
TRANSCRIPT_FILE="transcript-${TIMESTAMP}.md"
echo "$TRANSCRIPT_CONTENT" > "$TRANSCRIPT_FILE"
echo "✅ Transcript saved: $TRANSCRIPT_FILE"
echo ""
echo "✅ Transcription Complete!"
echo ""
echo "📊 Results:"
echo " File: $OUTPUT_FILE"
echo " Language: $LANGUAGE"
echo " Duration: $DURATION_HMS"
echo " Speakers: $NUM_SPEAKERS"
echo " Words: $WORD_COUNT"
echo " Processing time: ${ELAPSED_TIME}s"
echo ""
echo "🎯 Next steps:"
echo " 1. Review meeting minutes and action items"
echo " 2. Share report with participants"
echo " 3. Track action items to completion"
| Error | Likely Cause | Action |
|---|---|---|
| Transcription tool not found | faster-whisper/whisper not installed | Auto-install with pip install faster-whisper |
| Unsupported audio format | File extension not supported | Convert with ffmpeg automatically |
| File not found | Path is incorrect | Show exact path error; ask user to verify |
| File too large (>1 GB) | Very long recordings | Warn about processing time; offer to split |
| Low quality transcript | Poor audio quality | Report confidence issues |
| ffmpeg not found | ffmpeg not installed | Show install command: brew install ffmpeg |
User: Create meeting minutes from meeting-20260311.m4a
User: Convert all recordings/*.mp3 to text
User: Analyze this audio file and summarize it in English
Credits: Original skill by @ericgandrade - https://github.com/ericgandrade/claude-superskills
npx claudepluginhub inho-team/qe-framework --plugin qe-frameworkCreates, edits, and optimizes skills for Claude Code, including drafting, evaluating with test prompts, iterating on performance, and improving skill descriptions for better triggering accuracy.