markdown-video Checked

cd "{slides_directory}"
python /Users/lifidea/.claude/skills/markdown-video/slides_to_video.py \
  --slides-dir "slides-gemini" \
  --audio-dir "audio" \
  --output "{output_filename}.mp4"

---

Delta Updates

Both audio and image generation support **delta updates** - only regenerating what changed.

### How It Works

1. **Content hashing**: Each slide's content is hashed (MD5)

2. **Cache storage**: Hashes stored in .audio_cache.json / .slides_cache.json

3. **Change detection**: On subsequent runs, only changed slides are regenerated

4. **File verification**: Also checks if output file exists

### Example Output

✅ Found 20 slides
   20 slides with speaker notes

✨ Delta update: 17 slides unchanged, 3 to regenerate

🎵 Generating 3 audio files...
Progress |████████████████████████████████████████| 3/3 (100.0%)

✅ Audio generation complete!
   Generated: 3/3 files
   Unchanged: 17 files (skipped)

### Force Regeneration

To ignore cache and regenerate everything:

# Force regenerate all audio
python generate_audio.py "slides.md" --output-dir "audio" --force

# Force regenerate all images
python create_slides_gemini.py "slides.md" --output-dir "slides-gemini" --force

---

Quick Reference

### Full Workflow (First Run)

cd "{slides_directory}"

# Step 1: Generate audio
python /Users/lifidea/.claude/skills/markdown-video/generate_audio.py "slides.md" --output-dir "audio"

# Step 2: Generate slide images
python /Users/lifidea/.claude/skills/markdown-video/create_slides_gemini.py "slides.md" \
  --output-dir "slides-gemini" \
  --style "technical-diagram" \
  --auto-approve

# Step 3: Create video
python /Users/lifidea/.claude/skills/markdown-video/slides_to_video.py \
  --slides-dir "slides-gemini" \
  --audio-dir "audio" \
  --output "presentation.mp4"

### Update Workflow (After Changes)

Same commands - delta updates are automatic:

# Only regenerates changed slides
python generate_audio.py "slides.md" --output-dir "audio"
python create_slides_gemini.py "slides.md" --output-dir "slides-gemini" --auto-approve
python slides_to_video.py --slides-dir "slides-gemini" --audio-dir "audio" --output "presentation.mp4"

---

Requirements

### System Dependencies

• **Python 3.7+**
• **ffmpeg**: brew install ffmpeg

### Python Packages

pip install Pillow requests google-genai

### Environment Variables

export OPENAI_API_KEY="sk-..."
export GEMINI_API_KEY="..."

---

Cost Estimation

| Component | Cost | Example (20 slides) |

|-----------|------|---------------------|

| Gemini images | ~$0.04/slide | ~$0.80 |

| OpenAI TTS | ~$0.015/1K chars | ~$0.50 |

| **Total** | | ~$1.30 |

With delta updates, subsequent runs only cost for changed slides.

---

Error Handling

### No speaker notes found

• Slides need ^ prefixed speaker notes for narration
• Example: ^ This is the speaker note for this slide.

### Pronunciation problems

• Replace technical terms with phonetic equivalents in speaker notes
• Test with --dry-run first

### API errors

• Check API key environment variables
• Gemini rate limits: script includes 1-second delay between generations

---

Quality Checklist

Before marking complete:

• [ ] OpenAI and Gemini API keys configured
• [ ] Markdown file has speaker notes with ^ prefix
• [ ] Audio files generated successfully
• [ ] Slide images generated successfully
• [ ] Video plays correctly with synced audio
• [ ] Resolution is 1920x1080

---

Image Generation Mode

Two approaches for generating visuals:

| Mode | Script | Best For |

|------|--------|----------|

| **Slide-by-Slide** | create_slides_gemini.py | Standard presentations, precise control |

| **Section-based** | generate_section_images.py | Long presentations, infographic style |

### When to Use Section-Based

• Presentations with 20+ slides
• Content naturally groups into logical sections
• Prefer infographic overview per section vs. individual slides
• Want to reduce API costs (fewer images)

---

Section-Based Workflow (Alternative)

For presentations with many slides, generate one infographic image per section instead of per slide.

### Comparison

| Aspect | Slide-by-Slide | Section-Based |

|--------|---------------|---------------|

| Images | 1 per slide | 1 per section |

| Audio | Per slide | Per slide → merged by section |

| Review | Direct in markdown | Video script document |

| Best for | Short presentations | Long presentations (20+ slides) |

### Step 1: Generate Audio Files

Same as standard workflow:

cd "{slides_directory}"
python /Users/lifidea/.claude/skills/markdown-video/generate_audio.py "{slides_filename}" --output-dir "audio"

### Step 2: Generate Section Infographic Images

cd "{slides_directory}"
python /Users/lifidea/.claude/skills/markdown-video/generate_section_images.py "{slides_filename}" \
  --output-dir "slides-section" \
  --style "infographic"

**Style Options**:

| Style | Description |

|-------|-------------|

| infographic | Clean professional with icons (default) |

| professional | Minimalist corporate design |

| vibrant | Bright gradients for marketing |

| technical | Flowcharts and technical diagrams |

**Other Parameters**:

• --start-from N: Resume from se