Agent Skills
› opensquilla/opensquilla
› srt-from-script
srt-from-script
GitHub解析短视频脚本并生成带累积时间戳的SRT字幕文件。根据镜头时长和旁白文本计算时间点，支持尾部和头部偏移调整，确保字幕与视频画面精准同步且可读。
触发场景
需要将AI生成的短剧脚本转换为SRT字幕格式
在视频后期处理流程中需要为合并后的视频添加基于旁白的字幕
安装
npx skills add opensquilla/opensquilla --skill srt-from-script -g -y
SKILL.md
Frontmatter
{
"name": "srt-from-script",
"metadata": {
"opensquilla": {
"risk": "low",
"requires": {
"anyBins": [
"python",
"python3"
]
},
"capabilities": [
"filesystem-write"
]
}
},
"entrypoint": {
"args": [
"--output",
"{{ with.output_path }}",
"--gap-ms",
"{{ with.gap_ms | default(200) }}",
"--leading-offset-ms",
"{{ with.leading_offset_ms | default(0) }}"
],
"parse": "text",
"stdin": "{{ with.script }}",
"command": "python {baseDir}\/scripts\/build_srt.py",
"timeout": 30
},
"provenance": {
"origin": "opensquilla-original",
"license": "Apache-2.0"
},
"description": "Build an SRT subtitle file from a 3-shot short-drama script (ai-video-script OUTPUT FORMAT). Reads each SHOT_N block's DURATION_S + VOICEOVER, emits cumulative-timestamped SRT cues. Pure text-processing, no LLM, no network. Used by meta-short-drama between merge and the final subtitle-burn step.",
"description_zh": "从3镜头短剧脚本（ai-video-script输出格式）构建SRT字幕文件。读取每个SHOT_N块的DURATION_S和VOICEOVER，输出带累计时间戳的SRT字幕。纯文本处理，无LLM、无网络。由meta-short-drama在合并与最终字幕烧录步骤之间使用。",
"user-invocable": false,
"disable-model-invocation": true
}
srt-from-script
Parses an ai-video-script 3-shot script and writes an SRT subtitle file whose cues track the script's VOICEOVER per shot, time-coded with cumulative shot durations.
Inputs (with:)
| key | required | default | notes |
|---|---|---|---|
script |
yes | — | Full script text (the entire OUTPUT FORMAT block, including OVERVIEW + SHOT_1..N). Passed via stdin so the orchestrator does not need to write a temp file. |
output_path |
yes | — | Output .srt path. Parent dir created if missing. |
gap_ms |
no | 200 |
Tail pad subtracted from each cue's end so the subtitle vanishes ~200 ms before the next shot starts — avoids cuts clipping mid-character. |
leading_offset_ms |
no | 0 |
Shifts every cue forward by this many ms. Set to the cover/intro clip duration when the merged video prepends a title card before SHOT_1. |
Parsing rules
- A shot with
VOICEOVER: noneor empty contributes no SRT cue but itsDURATION_Sstill advances the timeline cursor. - Cue language follows the script verbatim. Chinese stays Chinese, English stays English — no translation.
- Cumulative timestamps: SHOT_1 starts at 00:00:00,000; SHOT_2 starts at SHOT_1.duration; etc.
- End time of each cue = next-shot start −
gap_ms, clamped to ≥ 800 ms after start so very short voiceover lines remain readable.
Output
Prints the absolute path of the written .srt on stdout.
The file is UTF-8 encoded so CJK voiceover lines survive when ffmpeg
reads them via the subtitles= filter.
Limits
- Assumes the script follows ai-video-script's strict OUTPUT FORMAT
(
=== SHOT_N ===blocks withDURATION_S:andVOICEOVER:fields). Drift away from that format → zero cues, exit 1. - 3-5 shots tested. Larger shot counts work but timestamps grow.
版本历史
- f662be3 当前 2026-07-31 11:49
- 7f72a32 2026-07-05 18:40
