安装

添加到你的 Claude Code skills 目录：

# Add to your Claude Code skills
git clone https://github.com/xwchris/videosays-agent-tools

安全报告

已验证

上次扫描：—

{
  "status": "PASSED",
  "issues": []
}

README.md

Videosays Agent Tools

Name: videosays-agent-tools
Author: xwchris

AI-agent-friendly CLI and SKILL.md package for video transcription, video to text, speech to text, subtitle extraction, and transcript export.

Videosays turns supported video links or share text into clean transcript text, timestamped timelines, SRT subtitles, and VTT subtitles. It is built for humans using a terminal and for AI agents using a skill.

中文：Videosays 是面向 AI Agent 和命令行用户的视频转文字工具，支持把公开视频链接或分享文本转成纯文本、带时间轴文本、SRT 字幕和 VTT 字幕。

Supported platforms include Douyin, TikTok, Instagram Reels, X (Twitter), Xiaohongshu, Bilibili, YouTube, and Kuaishou. Availability can vary by source video accessibility, region, platform restrictions, and whether captions or transcribable audio are available.

支持平台包括抖音、TikTok、Instagram Reels、X（Twitter）、小红书、Bilibili、YouTube、快手。实际可用性会受视频访问权限、地区、平台限制、字幕或音频可获取性影响。

This repository contains:

packages/cli - npm CLI package, exposed as the videosays command.
skills/videosays - canonical agent skill that calls npx videosays.
SKILL.md - root copy for directories that require a repository-root skill file, such as SkillsLLM.

Quick Start

npx videosays login
npx videosays transcribe "https://www.tiktok.com/@creator/video/123456"
npx videosays transcribe "https://www.bilibili.com/video/BV1234567890" --format srt

The CLI stores your API key in ~/.videosays. You can also provide it through VIDEOSAYS_API_KEY.

首次使用会打开浏览器授权，CLI 会把 API key 保存到 ~/.videosays。也可以通过 VIDEOSAYS_API_KEY 环境变量提供。

Repeated videos reuse the same account's active task or completed result by default, without another transcription charge. Every submission carries an idempotency key so a network retry returns the same resource. Use --force-new only when a fresh, normally billed transcription is required; keep using status commands for later checks.

Agent Skill

Use Videosays from an AI agent by giving it this prompt:

Read https://videosays.com/SKILL.md, install the Videosays Skill if your environment supports skills, and help me transcribe this public video link.

Or install the skill from this repository:

npx skills add xwchris/videosays-agent-tools

Install through ClawHub or SkillUse:

clawhub install @wegofuture/videosays
skilluse repo add xwchris/videosays-agent-tools --path skills --branch main --default
skilluse install videosays --agent codex --global

skills/videosays/SKILL.md is the canonical skill entry for registry distribution. The root SKILL.md and the website copy at https://videosays.com/SKILL.md should stay byte-for-byte in sync with it.

skills/videosays/SKILL.md 是分发平台使用的 canonical skill。根目录 SKILL.md 和网站公开版本 https://videosays.com/SKILL.md 需要保持同步。

Output Formats

videosays transcribe "<video-link-or-share-text>" --format text      # plain transcript, default
videosays transcribe "<video-link-or-share-text>" --format timeline  # timestamped segments
videosays transcribe "<video-link-or-share-text>" --format srt       # SRT subtitles
videosays transcribe "<video-link-or-share-text>" --format vtt       # VTT subtitles
videosays status "<task-id>" --format srt

输出格式：

text: 纯文本，默认格式
timeline: 带时间轴分段
srt: SRT 字幕
vtt: VTT 字幕

Skill Distribution

skills.sh / npx skills

skills.sh discovers skills from public GitHub repositories. This repository uses the standard skills/videosays/SKILL.md layout:

npx skills add xwchris/videosays-agent-tools
npx skills find videosays

ClawHub / OpenClaw

Install the published skill from the Wegofuture organization:

clawhub install @wegofuture/videosays
clawhub inspect @wegofuture/videosays

Publish updates after signing in to ClawHub with access to the wegofuture publisher:

clawhub login
clawhub skill publish skills/videosays --owner wegofuture

SkillUse

SkillUse can install skills from GitHub-backed repositories:

skilluse repo add xwchris/videosays-agent-tools --path skills --branch main --default
skilluse install videosays --agent codex --global

The --path skills flag is required because this repository keeps the canonical skill at skills/videosays/SKILL.md for registry compatibility. Omit --global if you want SkillUse to install into the current project's local agent skill directory instead.

Maintenance

Keep the canonical skill, root skill copy, and website copy in sync:

bash scripts/check-skill-sync.sh
VIDEOSAYS_PUBLIC_SKILL_PATH=/path/to/video2txt/packages/web/public/SKILL.md bash scripts/check-skill-sync.sh

SkillsLLM

SkillsLLM expects a SKILL.md file at the root of the submitted GitHub repository. Submit this repository URL and use the root SKILL.md copy:

https://github.com/xwchris/videosays-agent-tools

Commands

videosays login
videosays login --api-key <api-key>
videosays logout
videosays whoami
videosays transcribe <video-link-or-share-text>
videosays transcribe <video-link-or-share-text> --format text
videosays transcribe <video-link-or-share-text> --format timeline
videosays transcribe <video-link-or-share-text> --format srt
videosays transcribe <video-link-or-share-text> --format vtt
videosays status <taskId>
videosays status <taskId> --format srt
videosays batch <links.txt>
videosays batch status <batch-id>
videosays batch continue <batch-id>
videosays batch cancel <batch-id>
videosays balance
videosays history [limit]
videosays help

Batch progress checks use lightweight status responses. The CLI downloads complete Task results once at the end, and preserves completed work when a credit-limited batch is continued under the same Batch ID.

Links

Website: https://videosays.com/?utm_source=videosays_skill&utm_medium=agent_skill&utm_campaign=videosays_agent_skill
Public skill: https://videosays.com/SKILL.md
API docs: https://videosays.com/docs?utm_source=videosays_skill&utm_medium=agent_skill&utm_campaign=videosays_agent_skill&utm_content=api_docs
CLI package: videosays

License

MIT

常见问题

What is videosays-agent-tools?⌄

videosays-agent-tools is an open-source ai agents skill for AI coding assistants such as Claude Code, Codex CLI, and ChatGPT, built by xwchris. It has 0 GitHub stars.

Is videosays-agent-tools safe to use?⌄

Yes. videosays-agent-tools passed SkillsLLM's automated security scan — a dependency vulnerability audit plus prompt-injection heuristics — with no high-severity issues. You can read the full report in the Security Report section on this page.

How do I install videosays-agent-tools?⌄

Clone the repository with "git clone https://github.com/xwchris/videosays-agent-tools" and add it to your Claude Code skills directory (see the Installation section above). videosays-agent-tools ships a SKILL.md manifest, so compatible agents can discover and load it automatically.

What programming language is videosays-agent-tools written in?⌄

videosays-agent-tools is primarily written in JavaScript. It is open-source under xwchris on GitHub, so you can review or fork the full source.

Are there alternatives to videosays-agent-tools?⌄

Yes. SkillsLLM lists many other AI Agents skills you can browse and compare side by side. Open the AI Agents category from the badge at the top of this page, or use the Related Skills and comparison links further down to weigh videosays-agent-tools against similar tools.

videosays-agent-tools

安装

快速入门