Loading…
给任意视频加字幕的全流程——用 whisper.cpp 本地识别语音(自带逐句真实时间戳) → Claude 通读并纠正识别错误(同音字/专有名词) → 生成 SRT → 用带 libass 的 ffmpeg 把硬字幕烧录进视频。也支持把纯英文/外语视频自动翻译、配上「外语原文+中文」中外双语字幕(Claude 逐句翻译)。字号/字体/黑底白字/双语样式均可定制，可复用于不同视频。当用户要"给视频加字幕""识别视频语音生成字幕""视频转字幕""中英双语字幕/双语字幕""英文视频配中文字幕""字幕烧录/硬字幕/内嵌字幕""提取字幕""burn subtitles""bilingual subtitles""video subtitle"时使用。
video-subtitle is an agent skill entry in ChatHome Skills, sourced from GitHub Skill Search and scored 58/100. # 视频字幕全流程 (video-subtitle) 把任意视频做成带硬字幕的成片。**用 whisper.cpp 识别（时间轴准）+ Claude 纠错 + ffmpeg 烧录**。脚本在 `scripts/`，全部参数化、可复用于不同视频。 > **用户只提供视频**（外加可选的字号/字体/样式偏好）。**语音识别. As an agent skill, it packages a reusable instruction set that AI coding agents such as Codex and Claude Code can load to perform this task without hand-written glue code. ChatHome Skills discovered this entry through its daily ingest of official registries and GitHub discovery queries, and re-verifies repository facts, freshness signals, and install metadata on every run. The quality score weighs official-registry presence, a working install command, license clarity, GitHub star trajectory, and repository freshness — the full formula is on the Sources page. The install command above is ready to copy. Review the last-pushed date and repository status before adding video-subtitle to a production agent workflow; the snapshot facts below are point-in-time values from the most recent ingest.
codex skill install limin112/video-subtitleReview the upstream source before running this command.
Scan coverage: Install metadata and the indexed document body.
Automated signals from install metadata and a bounded skill body — not a full code security audit and not a recursive source or dependency review.
# 视频字幕全流程 (video-subtitle) 把任意视频做成带硬字幕的成片。**用 whisper.cpp 识别（时间轴准）+ Claude 纠错 + ffmpeg 烧录**。脚本在 `scripts/`，全部参数化、可复用于不同视频。 > **用户只提供视频**（外加可选的字号/字体/样式偏好）。**语音识别、专有名词识别、错别字纠正全部由你（Cl