Agent skill

Auto Subtitle

by ZJU-REAL in ZJU-REAL/Easel

自动字幕 / 语音转字幕:把音频或视频里的语音识别成字幕文件(SRT/ASS/TXT/JSON),可选把字幕烧录进视频。当用户说自动字幕、语音转字幕、视频加字幕、上字幕、转录、听写、字幕文件、生成字幕、烧字幕时使用。

Apache-2.0Auto-check passedMedia & Creative

Install Auto Subtitle

skills CLI
$ npx skills add ZJU-REAL/Easel --skill auto-subtitle -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install ZJU-REAL/Easel auto-subtitle --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/ZJU-REAL/Easel.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/openclaw/auto-subtitle .claude/skills/auto-subtitle && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
auto-subtitle
GitHub stars
3.4k
Token cost
~814 tokens
SKILL.md length
174 words
Files
2
Skills in repo
114
Repo updated
First seen
Licence
Apache-2.0

At a glance

自动字幕 / 语音转字幕:把音频或视频里的语音识别成字幕文件(SRT/ASS/TXT/JSON),可选把字幕烧录进视频。当用户说自动字幕、语音转字幕、视频加字幕、上字幕、转录、听写、字幕文件、生成字幕、烧字幕时使用。

  • Works in 2 steps: 生成字幕文件 → 产物与报告
  • Tasks that involve Transcription
  • SKILL.md covers 输入, 输出, 前置 and 执行步骤, plus 2 more sections
  • Calls python and ffmpeg

What it does

Auto Subtitle is an agent skill from ZJU-REAL/Easel. 自动字幕 / 语音转字幕:把音频或视频里的语音识别成字幕文件(SRT/ASS/TXT/JSON),可选把字幕烧录进视频。当用户说自动字幕、语音转字幕、视频加字幕、上字幕、转录、听写、字幕文件、生成字幕、烧字幕时使用。

Its SKILL.md is about 810 tokens, which your agent loads only when the skill is triggered. The skill folder holds 1 other file (for example `EASEL-META.md`).

It sits in Media & Creative, covering Transcription. It works with Whisper and FFmpeg. The repository describes itself as: An open-source AI agent for social media — discover trends, create content, publish everywhere, and learn what works across Xiaohongshu, Douyin, Zhihu, Bilibili, and more.🎨一个开源的… The licence is Apache-2.0.

When your agent uses it

  • Tasks that involve Transcription

Example prompts

  • “/auto-subtitle”

Requirements

  • Python 3

Workflow steps

2 steps, taken from the step headings in SKILL.md.

  1. 生成字幕文件
  2. 产物与报告

What it can do on your machine

Read from SKILL.md and the folder at commit 278f420. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Shell commands in SKILL.md call:

    • python
    • ffmpeg

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    Links to these hosts (documentation or services it may open):

    • github.com

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Auto Subtitle loads about 814 tokens when it runs. Until then it costs about 31 tokens; SKILL.md has 174 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~31
When it runs · the whole SKILL.md, loaded when a task matches
~814

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from ZJU-REAL/Easel at commit 278f420, republished under its Apache-2.0 licence (© ZJU-REAL). 174 words, ~814 tokens.

Download SKILL.mdSave it as .claude/skills/auto-subtitle/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.
name
auto-subtitle
description
自动字幕 / 语音转字幕:把音频或视频里的语音识别成字幕文件(SRT/ASS/TXT/JSON),可选把字幕烧录进视频。当用户说自动字幕、语音转字幕、视频加字幕、上字幕、转录、听写、字幕文件、生成字幕、烧字幕时使用。
layer
produce

自动字幕(语音转字幕)

把音频/视频里的人声识别成字幕。基于共享脚本 skills/shared/scripts/asr.py(faster-whisper 封装), 参数确定、可复现,做中文友好断句。可选把字幕烧录进视频(复用 skills/shared/scripts/video_ops.py / ffmpeg subtitles 滤镜)。

只做"语音 → 字幕文件 (+ 可选烧录)"。通用视频剪辑见 video-editing;纯降噪见 audio-denoise;长视频智能切片+烧字幕见 clipify。

输入

字段必填说明
input_file是音频或视频文件路径(视频自动提取音轨)
format否srt(默认)/ ass / txt / json
language否auto(默认)或 zh/en 等 ISO 639-1 码
model否tiny/base(默认)/small/medium/large-v3,越大越准越慢
burn否是否把字幕烧录进视频(需视频输入)

支持:mp3/wav/m4a/aac/flac 等音频;mp4/mkv/mov/webm 等视频。

输出

  • 字幕文件放入 outputs/主题名/(SRT/ASS/TXT/JSON)
  • 若烧录:带硬字幕的视频(*-sub.mp4)
  • 报告:识别语言、字幕条数、所用模型、输出路径

前置

  • 首次运行会从 HuggingFace 下模型,需外网代理。脚本读取 EASEL_PROXY 或 http(s)_proxy 环境变量作代理; 都未设则直连。也可先 export https_proxy=... http_proxy=... 指定。
  • CPU 环境用默认 --device cpu --compute-type int8 即可。

执行步骤

脚本路径(相对项目根):skills/shared/scripts/asr.py、skills/shared/scripts/video_ops.py。

1. 生成字幕文件
bash
# 视频 → SRT(自动提取音轨 + 自动检测语言)
python skills/shared/scripts/asr.py transcribe \
  -i input.mp4 -o outputs/主题名/input.srt --language zh

# 视频 → ASS(带样式,**字号/边距按视频横竖屏自适应**):视频输入自动探测宽高
python skills/shared/scripts/asr.py transcribe \
  -i input.mp4 -o outputs/主题名/input.ass --format ass --model small
# 纯音频 → ASS:无法探测尺寸,默认竖屏 1080x1920;横屏加 --res 1920x1080
python skills/shared/scripts/asr.py transcribe \
  -i voice.mp3 -o outputs/主题名/voice.ass --format ass --res 1920x1080
  • ASS 样式按目标视频宽高自适应:字号按短边(min(w,h)*0.05,竖/横屏都≈合适、不再横屏过大), 底边距按高、左右边距按宽,PlayRes=真实宽高。视频输入自动探测;纯音频用 --res 宽x高 指定。 要带样式的硬字幕优先烧这份 ASS(下节),比裸 SRT + 手填 force_style 更省心、且自适应。
  • 中文默认每行 ~18 字,超长自动断行/拆条;--max-line-chars 可调。
  • 不给 -o 时按输入文件名建项目目录,例如 talk.mp4 输出到 outputs/talk/talk.srt;已有项目应显式 -o outputs/主题名/<文件名>.<format>。
  • 查看可用模型/语言:python skills/shared/scripts/asr.py info。
2.(可选)把字幕烧录进视频

用户要"硬字幕/烧进视频"时,用 ffmpeg 的 subtitles(SRT)或 ass(ASS)滤镜:

bash
# 烧 SRT(可定制样式)
ffmpeg -y -i input.mp4 \
  -vf "subtitles=outputs/主题名/input.srt:force_style='FontName=Noto Sans CJK SC,FontSize=20,PrimaryColour=&H00FFFFFF,OutlineColour=&H80000000,BorderStyle=1,Outline=2'" \
  -c:a copy outputs/主题名/input-sub.mp4

# 烧 ASS(样式已在 ass 文件里,保真)
ffmpeg -y -i input.mp4 \
  -vf "ass=outputs/主题名/input.ass" \
  -c:a copy outputs/主题名/input-sub.mp4
  • 路径含特殊字符时,把 subtitles= 的值用单引号包裹并转义冒号。
  • 需要软字幕(可关闭)而非烧录:ffmpeg -i in.mp4 -i sub.srt -c copy -c:s mov_text out.mp4。
3. 产物与报告
  • 字幕文件、烧录视频均写入 outputs/主题名/。
  • 向用户报告:识别语言、字幕条数、模型、文件路径;提示可换 --model/--max-line-chars 重跑。

规则

  1. 视频先提取音轨 — 脚本自动用 ffmpeg 提取 16kHz 单声道 wav,不改原视频。
  2. 中文友好断句 — 按标点/长度断行,避免一行过长。
  3. 绝不删原文件 — 只产出新文件到 outputs/。
  4. 模型选择 — 求快用 base,求准用 small/medium;CPU 用 int8。
  5. 烧录需视频输入 — 纯音频无法烧录,只出字幕文件。
  6. 无 Profile 依赖 — 转录不需要账号画像。

自研参考

© ZJU-REAL, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 1 other file in skills/openclaw/auto-subtitle of ZJU-REAL/Easel.

  • SKILL.md
  • EASEL-META.md

Open the folder on GitHubat commit 278f420

Compare with similar skills

Auto Subtitle next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Auto Subtitle compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Auto Subtitle this skillZJU-REAL/Easel3.4k—~814Automated safety check: PassApache-2.0
ShortsAgriciDaniel/claude-shorts219—~3.2kAutomated safety check: NotesMIT
Bggg Tiktok Readvideobinggandata/bggg-skills605—~1.6kAutomated safety check: PassMIT
Watch Videocoreyhaines31/makerskills851—~3.8kAutomated safety check: PassMIT
Video Clippergooseworks-ai/goose-skills1.2k1 repos~3.1kAutomated safety check: NotesMIT
Use Local Whispersbusso/claudeclaw194—~1.3kAutomated safety check: NotesMIT

Similar skills

  • Shorts

    AgriciDaniel/claude-shorts

    Interactive longform-to-shortform video creator. An agent skill from AgriciDaniel/claude-shorts.

    219 GitHub stars~3.2k tokensUpdated 3 mo ago
    Media & CreativeAuto-check: notes
  • Bggg Tiktok Readvideo

    binggandata/bggg-skills

    把 TikTok、Reels、YouTube Shorts、UGC 广告、本地 MP4/MOV/WebM 等视频拆成 Codex 可读的视频上下文。

    605 GitHub stars~1.6k tokensUpdated 1 mo ago
    Media & CreativeAuto-check passed
  • Watch Video

    coreyhaines31/makerskills

    When you want to extract content from a video — YouTube, Loom, Vimeo, Riverside, Zoom recording, local MP4, X/IG video, anything yt-dlp supports.

    851 GitHub stars~3.8k tokensUpdated 2 days ago
    Media & CreativeAuto-check passed
  • Video Clipper

    gooseworks-ai/goose-skills

    Repurposes long-form video (podcasts, interviews, talks) into short-form vertical clips for Instagram Reels, TikTok, and YouTube Shorts.

    1.2k GitHub starsUsed in 1 repo~3.1k tokens
    Media & CreativeAuto-check: notes
  • Use Local Whisper

    sbusso/claudeclaw

    A skill your agent uses when the user wants local voice transcription instead of OpenAI Whisper API.

    194 GitHub stars~1.3k tokensUpdated 1 mo ago
    AI & LLM EngineeringAuto-check: notes
  • Transcribe Anything

    swyxio/skills

    Transcribes audio and video files to text using pluggable ASR backends.

    176 GitHub stars~8.5k tokensUpdated 6 days ago
    AI & LLM EngineeringAuto-check passed

More from ZJU-REAL/Easel

All 114 skills in this repo
  • Gzh Design

    ZJU-REAL/Easel

    微信公众号文章排版引擎:把 Markdown / Word(.docx) / PDF / 纯文本转成可直接粘贴进公众号编辑器的 HTML,自动章节编号、关键词标记、引言卡、目录、代码块、图片/GIF、作者签名;主题从 references/theme-index.md…

    3.4k GitHub stars~2.1k tokensUpdated today
    Auto-check passed
  • 微信公众号文章自动创作与发布工具。给定参考文章、文字或文档,自动搜索整理全网相关信息、生成图文并茂的公众号文章,并发布到微信公众号草稿箱。特别强调反 AI 检测写作。

    3.4k GitHub stars~1.8k tokensUpdated today
    Auto-check passed
  • Card Design

    ZJU-REAL/Easel

    社媒卡片视觉设计系统:提供配色、中文字体层级、满画幅布局、品类骨架和死空白/密度质检,避免模板化 PPT 与廉价 AI 感。

    3.4k GitHub stars~657 tokensUpdated today
    Auto-check passed
  • Ecom Details Image

    ZJU-REAL/Easel

    生成电商商品视觉方案:主图概念、场景图、详情页视觉方向和 AI 生图 Prompt. An agent skill from ZJU-REAL/Easel.

    3.4k GitHub stars~1.1k tokensUpdated today
    Auto-check: notes
  • Infographic

    ZJU-REAL/Easel

    将数据或文字内容转化为可视化信息图,支持静态(AntV)和动画 GIF 两种模式。当用户需要制作信息图、数据可视化、流程图、对比图、动画图表、GIF 图表、思维导图、SWOT 分析图时调用。本地渲染信息图/GIF 动画;要单张静态图片 URL 用 chart-visualization,要 CSV/JSON→整页报告用 data-report

    3.4k GitHub stars~643 tokensUpdated today
    Auto-check passed
  • Novel Writer

    ZJU-REAL/Easel

    长篇小说/网文连载创作:从世界观、人设和三级大纲写到逐章正文,并用文件化状态维护伏笔、前情和跨章一致性. An agent skill from ZJU-REAL/Easel.

    3.4k GitHub stars~1k tokensUpdated today
    Auto-check passed

Works with

Questions about Auto Subtitle

What does Auto Subtitle do?

自动字幕 / 语音转字幕:把音频或视频里的语音识别成字幕文件(SRT/ASS/TXT/JSON),可选把字幕烧录进视频。当用户说自动字幕、语音转字幕、视频加字幕、上字幕、转录、听写、字幕文件、生成字幕、烧字幕时使用。. Auto Subtitle is an agent skill from ZJU-REAL/Easel.

When should I use Auto Subtitle?

Auto Subtitle fits situations like: tasks that involve Transcription.

How do I install Auto Subtitle in Claude Code?

Run `npx skills add ZJU-REAL/Easel --skill auto-subtitle -a claude-code`. Or copy the skill folder (skills/openclaw/auto-subtitle in ZJU-REAL/Easel) into .claude/skills/auto-subtitle in your project. Claude Code loads it when a task matches its description.

How do I install Auto Subtitle in Codex?

Run `npx skills add ZJU-REAL/Easel --skill auto-subtitle -a codex`. Or copy the skill folder (skills/openclaw/auto-subtitle in ZJU-REAL/Easel) into .agents/skills/auto-subtitle in your project. Codex loads it when a task matches its description.

Can I use Auto Subtitle in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add ZJU-REAL/Easel --skill auto-subtitle -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/auto-subtitle, .gemini/skills/auto-subtitle, .github/skills/auto-subtitle and .opencode/skills/auto-subtitle in your project.

What does Auto Subtitle need to run?

Going by SKILL.md and its folder, Auto Subtitle needs the command-line tools its instructions call (python and ffmpeg). Our summary lists: Python 3.

Does Auto Subtitle access the network?

SKILL.md names 1 domain. As links in the text: github.com. This is read from the text; nothing was executed.

Is Auto Subtitle safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Auto Subtitle use?

Auto Subtitle is published under the Apache-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Auto Subtitle use?

About 814 tokens (SKILL.md is roughly 3.3k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Auto Subtitle?

Skills that share tags, products or a category with Auto Subtitle: Shorts (AgriciDaniel/claude-shorts, 219 stars), Bggg Tiktok Readvideo (binggandata/bggg-skills, 605 stars), Watch Video (coreyhaines31/makerskills, 851 stars) and Video Clipper (gooseworks-ai/goose-skills, 1.2k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Auto Subtitle?

ZJU-REAL (a GitHub organization) maintains it in ZJU-REAL/Easel, which has 3,376 GitHub stars. The repository holds 114 skills in this directory. The repository was last updated on October 9, 2026.

Source: ZJU-REAL/Easel on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.