anbeime/skill / skills/ancient-rap-battle/ancient-rap-battle
ancient-rap-battle
Verified古人说唱 Battle:把两个历史上的死对头(诸葛亮 vs 司马懿、岳飞 vs 秦桧……)做成一条 AI 说唱对决短视频,从选题写词(每句配史料注释)、Suno 做歌、Midjourney 定妆、即梦 Seedance 2.5 网页版分段生成(提示词按半句精确到 0.01 秒写歌词,口型一次对好),到自动逐镜头对齐、拼接、字幕包装、封面和发布文案一条龙。用户说"做一期 A vs B"、"古人说唱 battle"、"历史人物说唱"、"rap battle 视频",或者要改已有一期的歌词、镜头、字幕、封面时使用。Make an AI rap-battle short between two historical rivals, end to end, with Seedance 2.5 (or MiniMax H3).
scripts/clean_vocal.py
View on GitHub# -*- coding: utf-8 -*-
"""Step 6a - a cleaner, clearer vocal for lip sync (never used in the final mix).
usage: python scripts/clean_vocal.py <episode_dir>
htdemucs_ft separation (less music bleed than the default model) -> the same trim as 音乐_最终.wav
(work/grid.json keep) -> high-pass, less mud, presence boost, gentle compression, -16 LUFS.
Writes work/vocals_clean.wav, which seedance_packs.py cuts into the per-segment vocals.
"""
import glob
import os
import subprocess
import sys
sys.path.insert(0, os.path.dirname(os.path.abspath(__file__)))
from analyze_song import cut # noqa: E402
from common import die, jload, load_episode # noqa: E402
def main():
if len(sys.argv) < 2:
die("usage: clean_vocal.py <episode_dir>")
ep = sys.argv[1]
e = load_episode(ep)
work = os.path.join(ep, "work")
g = jload(os.path.join(work, "grid.json"))
out = glob.glob(os.path.join(work, "sep_ft", "htdemucs_ft", "*", "vocals.wav"))
if not out:
print("separating with htdemucs_ft (slower, ~5-10 min on CPU)...")
subprocess.run([sys.executable, "-m", "demucs", "-n", "htdemucs_ft", "--two-stems=vocals", "-o",
os.path.join(work, "sep_ft"), os.path.join(ep, e.get("song", "song.mp3"))], check=True)
out = glob.glob(os.path.join(work, "sep_ft", "htdemucs_ft", "*", "vocals.wav"))
tmp = os.path.join(work, "vocals_ft_cut.wav")
cut(out[0], g["keep"], tmp)
subprocess.run(["ffmpeg", "-v", "error", "-y", "-i", tmp, "-af",
"highpass=f=90,equalizer=f=250:t=q:w=1:g=-2,equalizer=f=3200:t=q:w=1.2:g=3,"
"acompressor=threshold=-20dB:ratio=3:attack=5:release=80,loudnorm=I=-16:TP=-1.5:LRA=7",
"-ar", "44100", os.path.join(work, "vocals_clean.wav")], check=True)
print("wrote work/vocals_clean.wav")
if __name__ == "__main__":
main()
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| slack-gif-creatoranthropics/skillsKnowledge and utilities for creating animated GIFs optimized for Slack. Provides constraints, validation tools, and animation concepts. Use when users request animated GIFs for Slack like "make me a GIF of X doing Y for Slack." | Stars: 198k | Updated | Claude CodeCodex | Verified | Install |
| ponytailDietrichGebert/ponytailLazy senior dev mode for any coding task: the smallest change that fully solves it, and a reply a busy human understands in one read. | Stars: 194k | Updated | Claude CodeCodex | Verified | Install |
| ponytail-debtDietrichGebert/ponytailHarvest every shortcut: comment into one debt ledger, so deferrals get tracked instead of forgotten. One-shot report. | Stars: 194k | Updated | Claude CodeCodex | Verified | Install |
| ponytail-debtDietrichGebert/ponytailList every `shortcut:` comment (and older `ponytail:` ones) as a debt ledger. One-shot report, changes nothing. Use for "ponytail debt", "what did ponytail defer", "list the shortcuts", /ponytail-debt. | Stars: 194k | Updated | Claude CodeCodex | Verified | Install |