music-to-storyboard
/music-to-storyboard — Music → Storyboard
Generate a shot-by-shot storyboard from music analysis, with shot types, camera movements, visual descriptions, mood, and transitions. Output is compatible with pull-film's storyboard-generator format.
Usage
/music-to-storyboard <audio_file_or_analysis_json>
Accepts either an audio file (runs analysis first) or a previously saved analysis JSON.
Steps
- Validate input (audio file or JSON)
- Generate storyboard:
python3 -m music_analyzer storyboard "<input_path>"
-
Present storyboard as a table or sequence:
- Shot # with section label and time range
- Shot type: wide, medium, close-up, etc.
- Camera movement: static, dolly, orbit, etc.
- Visual description (Chinese + English)
- Transition to next shot: cut, dissolve, fade
- Energy level and mood
-
Suggest using
/storyboard-generatorfrom pull-film to create the visual storyboard
Section → Shot Mapping
| Section | Default Shot | Camera | Visual Treatment |
|---|---|---|---|
| Intro | Wide → Medium | Slow dolly in | Environment establishing |
| Verse | Medium, Close-up | Static, slow pan | Narrative focus |
| Chorus | Wide, Close-up | Orbit, fast push | Visual climax |
| Bridge | Close-up, Wide | Slow dolly out | Contrast, reflection |
| Outro | Wide | Slow pull-out | Closure, fade |
Output Format
Compatible with pull-film's storyboard-generator:
{
"song_title": "example.mp3",
"total_duration": 240.5,
"bpm": 128.0,
"shots": [
{
"shot_number": 1,
"section": "intro",
"time_range": {"start": 0, "end": 15.5},
"shot_type": "wide",
"camera_movement": "slow dolly in",
"visual_description_zh": "...",
"visual_description_en": "...",
"transition": "fade",
"energy_level": 0.3
}
]
}
More from benzema216/dreamina-claude-skills
storyboard-generator
根据用户的创意/故事想法,批量生成多张连贯的图片和视频,并以专业分镜表(Storyboard)的形式展示。支持单镜头重新生成、图生视频、首尾帧视频生成等高级功能。适用于短视频脚本、动画分镜、广告创意、故事可视化等场景。
27storyboard-creator
小说/剧本转分镜表创作工具。将文字内容转换为详细的分镜表,用于指导AI生图和生视频。当用户需要:(1) 将小说章节转换为分镜表 (2) 创建AI生图用的分镜脚本 (3) 制作影视分镜规划 (4) 生成带有生图提示词的分镜表 时使用此技能。
14music-analyze
Full music analysis — extracts rhythm, emotion, timbre, tonality, lyrics and outputs structured JSON
6music-emotion
Analyze emotion — mood classification, energy, valence, genre detection
5music-timbre
Analyze timbre — MFCC, spectral features, loudness, source separation
4music-lyrics
Extract lyrics — timestamped transcription using faster-whisper
4