Hf Video
- 4 installs
- 15 repo stars
- Updated July 5, 2026
- xuanbingbingo/hf-video-kit
Automated talking-head video production line turning a script into a finished video with TTS or real voice, auto scene routing, and word-by-word subtitles.
About
An automated video production pipeline that turns a script into a finished narrated video with voiceover, auto-selected scenes, and word-level subtitles. A developer uses it to convert copy into vertical or horizontal videos.
- TTS or real-voice narration with character-level timeline alignment
- Auto scene routing (charts/code/flowcharts) and per-word subtitle highlighting
Hf Video by the numbers
- 4 all-time installs (skills.sh)
- Ranked #1,139 of 1,335 Generative Media skills by installs in the Skillselion catalog
- Data as of Jul 27, 2026 (Skillselion catalog sync)
npx skills add https://github.com/xuanbingbingo/hf-video-kit --skill hf-videoAdd your badge
Show developers this skill is listed on Skillselion. Paste this into your README.
| Installs | 4 |
|---|---|
| repo stars | ★ 15 |
| Last updated | July 5, 2026 |
| Repository | xuanbingbingo/hf-video-kit ↗ |
What it does
Automated talking-head video production line turning a script into a finished video with TTS or real voice, auto scene routing, and word-by-word subtitles.
Files
hf-video — 口播视频自动生产线
第一步（必做）
读取 ~/hf-video-kit/CLAUDE.md —— 那是本工作流的完整规则书（模式判定表、双模式流程、 场景判定表、视觉规范、硬规则、锚点工法、降级策略），本 skill 只是入口，一切以它为准。 先按 CLAUDE.md 顶部「模式判定」选模式：默认模式 A（AI 原生 TTS）； 用户说"用我的声音/真人版"或给了真人口播录像 → 模式 B（真人原声，工具在 tools/real/）。
若 ~/hf-video-kit/ 不存在，告知用户先 git clone https://github.com/xuanbingbingo/hf-video-kit.git 并运行 install.sh（Windows: install.ps1）。 若 ~/hf-video-kit/tools/.venv 不存在，先装环境：macOS 按 SETUP.md，Windows 10/11 按 SETUP-WINDOWS.md。
执行摘要（细节以 CLAUDE.md 为准）
1. 数据核实：文案涉及行业数字先联网核实标 SOURCE，查不到标 DEMO 2. 文案：口语化；扫多音字（行/重/长/还/得 等） 3. 配音+字级时间轴： ~/hf-video-kit/tools/.venv/bin/python ~/hf-video-kit/tools/gen_voice_timed.py script.md assets/voice.wav assets/transcript_chars.json 沉稳解说 4. 场景路由：新 episode 建在 ~/hf-video-kit/episodes/episode-NN/； 拷贝 ~/hf-video-kit/tools/project-scaffold/ 为其 hf-project/，按判定表逐段加场景 5. 锚点：场景边界=句子 start，段内元素卡关键词出口瞬间；改一字=全片锚点语义重算 6. 渲染：validate → snapshot 抽帧自检 → npx --yes hyperframes@0.6.84 render → 必须 open（Win: start）打开
硬规则速记（违反不许出片）
必须有配音（含 demo）／字幕零标点／多音字先扫／数据真实标来源／渲染前抽帧自检渲染后打开
Related skills
Remotion Best PracticesGet Remotion-specific coding guidance that prevents common video rendering mistakes when creating animated React videos.451k4.2k
Ai Video GenerationGenerate videos using 40+ AI models including Veo, Seedance, and others via inference.sh442k665Ai Image GenerationGenerate images using 50+ AI models including FLUX, Gemini, and Replicate via inference.sh441k665Ai Avatar VideoGenerate videos featuring AI avatars for product demos, tutorials, marketing, or explainers441k665Remotion RenderRender videos programmatically using React components and Remotion framework441k665
Remotion RenderGenerate high-quality MP4 videos from React code using Remotion inside an AI coding agent.363k665