music-lyrics

📁 benzema216/dreamina-claude-skills 📅 8 days ago
4
总安装量
4
周安装量
#48323
全站排名
安装命令
npx skills add https://github.com/benzema216/dreamina-claude-skills --skill music-lyrics

Agent 安装分布

opencode 3
replit 2
claude-code 2
openclaw 1
trae 1

Skill 文档

/music-lyrics — Lyrics Transcription

Transcribe lyrics from audio with timestamps using faster-whisper (when available).

Usage

/music-lyrics <audio_file_path>

Steps

  1. Validate the audio file path
  2. Run lyrics extraction:
python3 -m music_analyzer lyrics "<audio_file_path>"

Optionally specify model size: --model-size base (tiny/base/small/medium/large-v2)

  1. Present results:
    • Has Vocals: Whether vocals were detected
    • Language: Detected language
    • Lyrics: Timestamped segments with text
    • Full Text: Complete concatenated lyrics

Requirements

  • Full tier: faster-whisper must be installed for actual transcription
  • Lite tier: Only vocal detection heuristic (no transcription)

Install full dependencies:

pip install -e "~/.claude/plugins/music-analyzer/src/[full]"

Output Fields

Field Description
segments Array of {start, end, text, confidence}
full_text Complete lyrics text
language Detected language code
has_vocals Boolean — vocals detected
method “whisper” or “none”