autoRecording
Health Uyari
- License — License: MIT
- Description — Repository has a description
- Active repo — Last push 0 days ago
- Low visibility — Only 5 GitHub stars
Code Gecti
- Code scan — Scanned 7 files during light audit, no dangerous patterns found
Permissions Gecti
- Permissions — No dangerous permissions requested
Bu listing icin henuz AI raporu yok.
A Claude Code skill that records, renders and narrates polished demo videos of web apps.
autoRecording
Record a polished, narrated demo video of a web app — from one Python story file.
用一个 Python 分镜文件,把 Web 应用做成带解说的演示视频。
▶ 1 分钟演示 · 示例:督办证据工作台(任务、部门、材料均为模拟数据) · 直接播放 MP4
What it is
A Claude Code skill and standalone Python pipeline that turns a web app into a finished demo video. You write a
story file that says what to show and say; the scripts record the app, render the video, add the narration,
and check the result.
- Record — Playwright drives a headless Chromium through clicks, typing, scrolling and waits. The app runs as
a throwaway instance with its own port and data. - Render — 1920×1080 at 60 fps, with camera moves, outlines, spotlights, numbered steps, chapters and captions.
- Narrate — local Qwen3-TTS, one stable Mandarin voice, each line fitted to its caption.
- Verify — marked regions, label placement, caption fit, whisper transcription, speaker similarity, and
packet hashes proving the picture was not re-encoded.
Install and quick start
git clone https://github.com/OrrrGE/autoRecording \
~/.claude/skills/autoDemoRecordingSkill
cd ~/.claude/skills/autoDemoRecordingSkill
python3 scripts/demo_env.py setup
PY=~/.cache/auto-demo-recording/venv/bin/python
$PY scripts/demo_record.py --story examples/selftest/story.py --work /tmp/demo-selftest
$PY scripts/demo_render.py --work /tmp/demo-selftest --check
$PY scripts/demo_render.py --work /tmp/demo-selftest --out /tmp/demo-selftest/selftest.mp4
$PY scripts/demo_voice.py --work /tmp/demo-selftest # needs a GPU + speech models
Recording and rendering need no GPU. Full tutorial: README.en.md.
Use it for your app
Copy story_template.py, fill in TITLE, CHAPTERS and launch(), then direct the video
with d.say, d.click, d.zoom, d.mark and d.until. Full API: references/director.md.
Narration options: references/narration.md. Installation:references/environment.md.
中文 · 点击切换Record a throwaway instance with sample data. Frames are real screenshots; do not commit
work/.
这是什么
一个 Claude Code 技能,也是一组独立的 Python 脚本:把 Web 应用做成完整的演示视频。你只需要写一个
story 文件说明演示什么、说什么,录制、渲染、配音和核验都由脚本完成。
- 录制:Playwright 驱动无头 Chromium,按 story 点击、输入、滚动、等待;应用以临时实例运行,独占端口和数据。
- 渲染:1920×1080、60 fps,带镜头推近、框选、聚焦压暗、编号步骤、章节条和字幕。
- 配音:本地 Qwen3-TTS,同一个稳定的普通话音色,逐句贴合字幕时长。
- 核验:标注内容与颜色、标注文字位置、字幕是否放得下、Whisper 听写、CAM++ 声纹,以及证明画面未被重新编码的包哈希。
安装与快速开始
git clone https://github.com/OrrrGE/autoRecording \
~/.claude/skills/autoDemoRecordingSkill
cd ~/.claude/skills/autoDemoRecordingSkill
python3 scripts/demo_env.py setup
PY=~/.cache/auto-demo-recording/venv/bin/python
$PY scripts/demo_record.py --story examples/selftest/story.py --work /tmp/demo-selftest
$PY scripts/demo_render.py --work /tmp/demo-selftest --check
$PY scripts/demo_render.py --work /tmp/demo-selftest --out /tmp/demo-selftest/selftest.mp4
$PY scripts/demo_voice.py --work /tmp/demo-selftest # 需要显卡和语音模型
录制和渲染不需要显卡。完整教程见 README.zh-CN.md。
给自己的应用做视频
复制 story_template.py,填 TITLE、CHAPTERS、launch(),然后用d.say、d.click、d.zoom、d.mark、d.until 写分镜。完整 API 见references/director.md,配音设置见references/narration.md,安装见references/environment.md。
Yorumlar (0)
Yorum birakmak icin giris yap.
Yorum birakSonuc bulunamadi