ericgandrade/claude-superskills/audio-transcriber

# 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

echo "⚠️  No transcription tool found"
echo ""
echo "🔧 Auto-install dependencies? (Recommended)"
read -p "Run installation script? [Y/n]: " AUTO_INSTALL
 
if [[ ! "$AUTO_INSTALL" =~ ^[Nn] ]]; then
    # Get skill directory (works for both repo and symlinked installations)
    SKILL_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
    
    # Run installation script
    if [[ -f "$SKILL_DIR/scripts/install-requirements.sh" ]]; then
        bash "$SKILL_DIR/scripts/install-requirements.sh"
    else
        echo "❌ Installation script not found"
        echo ""
        echo "📦 Manual installation:"
        echo "  pip install faster-whisper  # Recommended"
        echo "  pip install openai-whisper  # Alternative"
        echo "  brew install ffmpeg         # Optional (macOS)"
        exit 1
    fi
    
    # Verify installation succeeded
    if python3 -c "import faster_whisper" 2>/dev/null || python3 -c "import whisper" 2>/dev/null; then
        echo "✅ Installation successful! Proceeding with transcription..."
    else
        echo "❌ Installation failed. Please install manually."
        exit 1
    fi
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

if [[ ! -f "$AUDIO_FILE" ]]; then
    echo "❌ File not found: $AUDIO_FILE"
    exit 1
fi

# Get file size
FILE_SIZE=$(du -h "$AUDIO_FILE" | cut -f1)
 
# Get duration and format using ffprobe
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)
 
# Convert duration to HH:MM:SS
DURATION_HMS=$(date -u -r "$DURATION" +%H:%M:%S 2>/dev/null || echo "Unknown")

SIZE_MB=$(du -m "$AUDIO_FILE" | cut -f1)
if [[ $SIZE_MB -gt 25 ]]; then
    echo "⚠️  Large file ($FILE_SIZE) - processing may take several minutes"
fi

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

# 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}
 
2.**{topic_2}** ({timestamp})
   -{key_point_1}
 
### Decisions Made
-✅ {decision_1}
-✅ {decision_2}
 
### Action Items
-[ ] **{action_1}** - Assigned to: {speaker} - Due: {date_if_mentioned}
-[ ] **{action_2}** - Assigned to: {speaker}
 
 
*Generated by audio-transcriber skill v1.0.0*  
*Transcription engine: {engine} | Processing time: {elapsed_time}s*

# {AgentName} — Transcript Analysis Agent
Role: Analyze the transcript below and extract ONLY {topic/action items/decisions}. Return structured list with timestamps.
Input: [full transcript text with speaker labels]

def generate_meeting_minutes(segments):
    """Extract topics, decisions, action items from transcription."""
    
    # Group segments by topic (simple clustering by timestamps)
    topics = cluster_by_topic(segments)
    
    # Identify action items (keywords: "should", "will", "need to", "action")
    action_items = extract_action_items(segments)
    
    # Identify decisions (keywords: "decided", "agreed", "approved")
    decisions = extract_decisions(segments)
    
    return {
        "topics": topics,
        "decisions": decisions,
        "action_items": action_items
    }
def generate_summary(segments, max_paragraphs=5):
    """Create executive summary using AI (Claude/GPT via API or local model)."""
    
    full_text = " ".join([s["text"] for s in segments])
    
    # Use Chain of Density approach (from prompt-engineer frameworks)
    summary_prompt = f"""
    Summarize the following transcription in {max_paragraphs} concise paragraphs.
    Focus on key topics, decisions, and action items.
    
    Transcription:
    {full_text}
    """
    
    # Call AI model (placeholder - user can integrate Claude API or use local model)
    summary = call_ai_model(summary_prompt)
    
    return summary

# v1.1.0: Use timestamp to avoid overwriting
TIMESTAMP=$(date +%Y%m%d-%H%M%S)
TRANSCRIPT_FILE="transcript-${TIMESTAMP}.md"
SUMMARY_FILE="summary-${TIMESTAMP}.md"
 
echo "$TRANSCRIPT_CONTENT" > "$TRANSCRIPT_FILE"
echo "✅ Transcript saved: $TRANSCRIPT_FILE"
 
if [[ -n "$SUMMARY_CONTENT" ]]; then
    echo "$SUMMARY_CONTENT" > "$SUMMARY_FILE"
    echo "✅ Summary saved: $SUMMARY_FILE"
fi

from rich.progress import Progress, SpinnerColumn, TextColumn
def process_with_llm(transcript, prompt, cli_tool='claude'):
    full_prompt = f"{prompt}\n\n---\n\nTranscription:\n\n{transcript}"
    with Progress(
        SpinnerColumn(),
        TextColumn("[progress.description]{task.description}"),
        transient=True
    ) as progress:
        progress.add_task(
            description=f"🤖 Processing with {cli_tool}...",
            total=None
        )
        
        if cli_tool == 'claude':
            result = subprocess.run(
                ['claude', '-'],
                input=full_prompt,
                capture_output=True,
                text=True,
                timeout=300  # 5 minutes
            )
        elif cli_tool == 'gh-copilot':
            result = subprocess.run(
                ['gh', 'copilot', 'suggest', '-t', 'shell', full_prompt],
                capture_output=True,
                text=True,
                timeout=300
            )
    
    if result.returncode == 0:
        return result.stdout.strip()
    else:
        return None

🤖 Processing with claude... ⠋
[After completion:]
✅ Summary generated successfully!

💾 Saving files...