Summary
This handles the full subtitle workflow for Chinese videos: transcribes with Whisper, applies dictionary corrections for brand names and technical terms, outputs clean text in 15-character lines for review, then matches your edits back to timestamps and burns them in with FFmpeg. The two-pass approach is smart because automated transcription always needs human review, especially for proper nouns. It enforces sensible rules like no line breaks mid-screen and no trailing punctuation. You can tweak styling (yellow text, larger fonts, top positioning) but the default white-on-black works for most cases. If you're cutting Chinese content and tired of manually syncing subtitle edits, this compresses a tedious multi-tool process into one flow.
Install to Claude Code
npx -y skills add zrt-ai-lab/opencode-skills --skill videocut-subtitle --agent claude-codeInstalls into .claude/skills of the current project.
Plug Mailtrap into your AI workflow and let it handle the email.
Connect Mailtrap MCP →
Agent, run crypto. Access onchain data & trade routes via 1inch.
Install now →
Make coding agent sessions - Searchable, Shareable, Vendor-neutral & Scored.
Try For Free →
Your agent targets a perfect 10 Code Health score. Deterministic. Every commit.
Try For Free →
Integrate web data into your AI product. One API to scrape website & brand data.
Get API Key Now →
belt cli automatically finds the best tools and skills for your agent. image, video, music, tts...
one prompt install →
Files
SKILL.mdView on GitHub
字幕
转录 → 纠错 → 审核 → 匹配 → 烧录
流程
1. 转录视频（Whisper）
↓
2. 词典纠错 + 分句
↓
3. 输出字幕稿（纯文本，一句一行）
↓
【用户审核修改】
↓
4. 用户给回修改后的文本
↓
5. 我匹配时间戳 → 生成 SRT
↓
6. 烧录字幕（FFmpeg）
转录
使用 OpenAI Whisper 模型进行语音转文字：
whisper video.mp4 --model medium --language zh --output_format json
| 模型 | 用途 |
|---|---|
medium | 默认，平衡速度与准确率 |
large-v3 | 高精度，较慢 |
输出 JSON 包含逐词时间戳，用于后续 SRT 生成。
字幕规范
| 规则 | 说明 |
|---|---|
| 一屏一行 | 不换行，不堆叠 |
| ≤15字/行 | 超过15字必须拆分（4:3竖屏） |
| 句尾无标点 | 你好 不是 你好。 |
| 句中保留标点 | 先点这里，再点那里 |
词典纠错
读取 词典.txt，每行一个正确写法：
skills
Claude
iPhone
我自动识别变体：claude → Claude
字幕稿格式
我给用户的（纯文本，≤15字/行）：
今天给大家分享一个技巧
很多人可能不知道
其实这个功能
藏在设置里面
你只要点击这里
就能看到了
用户修改后给回我，我再匹配时间戳生成 SRT。
样式
默认：24号白字、黑色描边、底部居中
可选样式：
| 样式 | 说明 |
|---|---|
| 默认 | 白字黑边 |
| 黄字 | 黄字黑边（醒目） |
用户可说：
- "字大一点" → 32号
- "放顶部" → 顶部居中
- "黄色字幕" → 黄字黑边
输出
01-xxx_字幕稿.txt # 纯文本，用户编辑
01-xxx.srt # 字幕文件
01-xxx-字幕.mp4 # 带字幕视频
Featured
Plug Mailtrap into your AI workflow and let it handle the email.
Connect Mailtrap MCP →Agent, run crypto. Access onchain data & trade routes via 1inch.
Install now →Make coding agent sessions - Searchable, Shareable, Vendor-neutral & Scored.
Try For Free →Your agent targets a perfect 10 Code Health score. Deterministic. Every commit.
Try For Free →Integrate web data into your AI product. One API to scrape website & brand data.
Get API Key Now →belt cli automatically finds the best tools and skills for your agent. image, video, music, tts...
one prompt install →
