zenstory-ai/video-recap-skills / skills/video-recap
video-recap
Verified把一段或多集视频做成带画框字幕的中文解说成片或纯原声高光短片。用户提供 .mp4 / .mov / .mkv / .webm,要求做影视解说、短剧二创、加旁白配音、跨集混剪或导出剪映草稿时使用;串联完成看片识台词、定主线与留原声、按台词停顿切镜头、写词检查、TTS 配音与混音加字幕。触发词:视频解说、影视解说、视频旁白、生成解说、视频 recap、video recap、voiceover、narration、recap。
scripts/timeline_emit.py
View on GitHub"""Backend-neutral timeline emission for assemble.py."""
from pathlib import Path
from audio_mix import _seg_place_window
from lib import CONFIG, log
from media import _build_video_clips
from source_subtitles import _combined_subtitle_entries
from subtitles.core import _effective_subtitle_style
from timeline import build_timeline, save_timeline
import packaging
def _timeline_subtitle_segments(tts_segments, work_dir, duration_s, canvas=None):
"""Display-ready subtitle cues for timeline/export text tracks.
The narration audio track keeps raw semantic text for editor reference; this
payload mirrors SRT/ASS display policy, including terminal-punctuation cleanup
and original-dialogue gap subtitles when configured.
"""
style = _effective_subtitle_style(canvas, work_dir) if canvas is not None else None
if (
style is None
or (
int(style["max_chars"]) == int(CONFIG["subtitle_max_chars"])
and float(style.get("bridge_gap_seconds", 0.0)) <= 0.0
and not packaging.has_packaging_plan(work_dir)
)
):
entries = _combined_subtitle_entries(tts_segments, work_dir, duration_s)
else:
entries = _combined_subtitle_entries(
tts_segments, work_dir, duration_s,
max_chars=int(style["max_chars"]),
bridge_gap_seconds=float(style.get("bridge_gap_seconds", 0.0)),
)
return [
{
"text": entry["text"],
"timeline_start": float(entry["start"]),
"timeline_end": float(entry["end"]),
}
for entry in entries
]
def _emit_timeline(input_video, tts_segments, work_dir, duration_s, canvas, has_bgm, *,
audio_mode="narration", studio_packaging=None):
"""Build and persist the backend-neutral multi-track timeline.json."""
if audio_mode == "narration":
video_clips = _build_video_clips(input_video, work_dir, duration_s)
else:
# Non-narration sound comes from the actual current picture input as one
# complete interval. Re-expanding an old cut plan would substitute different
# source sound and make the optional editor project misrepresent the render.
video_clips = [{
"source_path": str(Path(input_video)),
"source_start": 0.0,
"source_end": float(duration_s),
"timeline_start": 0.0,
"timeline_end": float(duration_s),
}]
narration_segments = []
for seg in tts_segments:
placed = seg.get("placed_audio_path")
if not placed:
continue
s, e = _seg_place_window(seg)
narration_item = {
# JianYing must consume the exact WAV written into narration.wav. In
# particular, a tempo-adjusted beat cannot reference its longer pre-fit
# source or the editor will trim its final words at timeline_end.
"source_path": str(Path(placed)),
"timeline_start": s, "timeline_end": e,
"text": seg["narration"],
"overlaps_speech": seg["overlaps_speech"],
"gain": 1.0,
}
for key in ("source_duck_end", "source_restore_at", "source_handoff_status", "source_entry_status"):
if key in seg:
narration_item[key] = seg[key]
narration_segments.append(narration_item)
fade = CONFIG["duck_fade_seconds"]
bgm = None
if has_bgm:
bgm = {"source_path": CONFIG["bgm_path"],
"volume": CONFIG["bgm_volume"],
"ducking_volume": CONFIG["bgm_ducking_volume"],
"fade": fade}
# narration mode always ducks; the draft carries the same envelope as editable
# volume keyframes (ffmpeg stays the canonical mix)
ducking = None
if audio_mode == "narration":
ducking = {"idle": CONFIG["idle_orig_volume"],
"speech": CONFIG["speech_ducking_volume"],
"quiet": CONFIG["zone_ducking_volume"],
"fade": fade,
"bridge": CONFIG["duck_bridge_seconds"]}
subtitle_segments = _timeline_subtitle_segments(tts_segments, work_dir, duration_s, canvas)
image_segments = (
packaging.studio_timeline_segments(studio_packaging, duration_s)
+ packaging.timeline_image_segments(
packaging.load_packaging_layers(work_dir, canvas), canvas, duration_s
)
)
timeline = build_timeline(canvas, duration_s, video_clips,
narration_segments, bgm=bgm, ducking=ducking,
subtitle_segments=subtitle_segments,
image_segments=image_segments)
if audio_mode != "narration":
for clip in timeline["tracks"][0]["clips"]:
clip["audio"]["base_gain"] = round(float(CONFIG["idle_orig_volume"]), 4)
degraded = [
{"source_path": clip["source_path"], "reason": clip["provenance_reason"]}
for clip in video_clips
if clip.get("provenance_degraded")
]
if degraded:
timeline["provenance"] = {"degraded": True, "degraded_clips": degraded}
log(f" ⚠️ 时间线 provenance 降级: {degraded[0]['reason']} ({len(degraded)} clip)")
else:
timeline["provenance"] = {"degraded": False}
out = Path(work_dir) / "timeline.json"
save_timeline(timeline, out)
log(f"时间线模型: {out} ({len(timeline['tracks'])} 轨)")
return timeline
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: 196k | 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: 196k | 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: 196k | Updated | Claude CodeCodex | Verified | Install |