← Back to Skills Marketplace
150
Downloads
0
Stars
0
Active Installs
5
Versions
Install in OpenClaw
/install jiuma-free-video-to-text
Description
九码AI免费抖音视频下载和文本提取技能。
README (SKILL.md)
jiuma-free-video-to-text Skill
这是一个免费抖音视频文本提取工具,基于九马(Jiuma)平台。输入抖音短视频的地址或分享链接,解析返回视频的下载链接, 还可以继续提取短视频的文本内容。
功能特性
- 下载视频:输入抖音短视频地址或分享链接,解析返回视频的下载地址
- 📝 视频转文本:提取视频的文本内容
安装要求
- Python版本:3.10 或更高版本
- 依赖库:
requests库
工作流程
- 第一步:询问用户提供视频的下载地址
- 第二步:询问用户是否需要提取视频文案, 如果用户不需要或者不回答,则流程结束
- 第三步:提交视频提取文本任务
- 第四步:定时查询状态并返回结果
参数说明
| 参数名 | 类型 | 是否必需 | 描述 |
|---|---|---|---|
video_url |
string | ✅️ 是 | 抖音视频地址或者分享链接地址 |
final_video_url |
string | ❌️ 否 | 对video_url解析后的最终地址 |
task_id |
string | ❌️ 否 | 查询任务状态 |
使用指南
当用户需要提取抖音视频文本或者下载抖音视频时,按照以下步骤操作:
1. 收集用户信息
video_url:
- 提示用户输入抖音视频播放地址或者分享链接地址
- 示例:
video_url="https://www.douyin.com/jingxuan/course?modal_id=7563552305543482624"或video_url="1.51 [email protected] Agb:/ 08/10 演傻子这一块,还得是熊二最权威 # 熊出没 # 熊二 # 充能计划 # 动漫 # 青年创作者成长计划 https://v.douyin.com/6Pc1GtnQp2o/ 复制此链接,打开Dou音搜索,直接观看视频!"
2. 执行生成
- 解析video_url地址
# OpenClaw中使用
# 解析视频地址
python3 ./skills/jiuma-free-video-to-text/video_to_text.py --action "parse" --video_url "{{.video_url}}"
- 提交视频提取文本任务
# OpenClaw中使用
# 提交视频提取文本任务
python3 ./skills/jiuma-free-video-to-text/video_to_text.py --action "create" --final_video_url "{{.final_video_url}}"
- 查询视频提取文本任务状态
# OpenClaw中使用
# 查询视频提取文本状态
python3 ./skills/jiuma-free-video-to-text/video_to_text.py --action "check" --task_id {{.task_id}}
API说明
解析视频地址
- 执行命令:
python3 ./skills/jiuma-free-video-to-text/video_to_text.py --action "parse" --video_url "{{.video_url}}" - 参数:
action: 操作类型, parse表示解析视频地址,create表示提交视频提取文本任务; check表示查询视频提取文本状态video_url: 用户输入的视频地址
- 响应结果:
code: 状态码, 200表示成功; 500表示失败error: 错误信息final_video_url: 视频的最终解析地址download_video_url: 视频下载地址
视频提取文本
- 执行命令:
python3 ./skills/jiuma-free-video-to-text/video_to_text.py --action "create" --final_video_url "{{.final_video_url}}" - 参数:
action: 操作类型, parse表示解析视频地址,create表示提交视频提取文本任务; check表示查询视频提取文本状态final_video_url: 视频的最终解析地址
- 响应结果:
code: 状态码, 200表示成功; 500表示失败error: 错误信息task_id: 任务ID
查看任务的状态
- 执行命令:
python3 ./skills/jiuma-free-video-to-text/video_to_text.py --action "check" --task_id {{.task_id}}" - 参数:
action: 操作类型, parse表示解析视频地址,create表示提交视频提取文本任务; check表示查询视频提取文本状态task_id: 任务id
- 响应结果:
code: 状态码, 200表示成功; 500表示失败error: 错误信息content: 文本内容
交互流程优化
智能引导
- 第一步:询问用户提供视频的下载地址, 展开视频下载地址的详情
- 第二步:询问用户是否需要提取视频文案, 如果用户不需要,则流程结束
- 第三步:提交视频提取文本任务
- 第四步:定时查询状态并返回结果
错误预防
- web url格式验证
- 生成前二次确认
最佳实践
注意事项
- 不同视频时长的提取时间不一样, 需要耐心等待
- 确保网络连接稳定
- 如需中断生成,请使用适当的中断方式
Usage Guidance
This skill appears to do exactly what it claims: it posts the Douyin/TikTok link you provide to a Jiuma API to resolve download URLs and to extract text. Before installing, consider: 1) privacy — you are sending video URLs (and any sensitive info they contain) to https://api.jiuma.com; do you trust that service and its retention/usage policies? 2) legality — downloading or extracting text from some videos may violate platform terms or copyright. 3) runtime requirements — it needs Python 3.10+ and the requests library. If you are uncomfortable sending links to the external API, do not install or run the skill, or run it in an isolated environment and inspect network traffic first.
Capability Assessment
Purpose & Capability
Name/description, SKILL.md runtime instructions, and the Python implementation all align: they parse a supplied Douyin URL, call a Jiuma API (https://api.jiuma.com) to resolve/download and to create/check a text extraction task. No unrelated credentials, binaries, or config paths are requested.
Instruction Scope
SKILL.md instructs the agent to collect a video_url and run the included script with actions parse/create/check. The instructions do not request arbitrary file reads, environment secrets, or other system state beyond calling the script and awaiting network responses.
Install Mechanism
This is an instruction + single Python script bundle with no install spec. It requires Python 3.10+ and the requests library as documented — nothing is downloaded or extracted by the skill itself.
Credentials
No environment variables or credentials are requested, which is proportional. However, the script sends user-supplied video URLs to a third-party API (https://api.jiuma.com). This is expected for the stated purpose but is a privacy consideration: video content or metadata provided in URLs will be transmitted off‑device.
Persistence & Privilege
The skill does not request always:true, does not modify other skills or system settings, and has no install-time privileges. It operates on-demand via the included script.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install jiuma-free-video-to-text - After installation, invoke the skill by name or use
/jiuma-free-video-to-text - Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.4
- No changes detected in this version.
- All skill features, documentation, and workflow remain the same as the previous version.
v1.0.3
- 文档微调:在使用指南部分,将“抖音视频地址或者分享链接地址”调整为“抖音视频播放地址或者分享链接地址”以提高清晰度。
- 未检测到代码或功能改动,仅对文档描述进行了优化和修正。
v1.0.2
- Renamed the skill from "jiuma-free-speech-to-text" to "jiuma-free-video-to-text" for better clarity.
- Updated all usage instructions and code paths to reflect the new skill name.
- No functional or code changes; only documentation updates for the new naming.
v1.0.1
- No changes detected in this version.
- All features and documentation remain the same as the previous release.
v1.0.0
- Initial release of jiuma-free-speech-to-text skill.
- Supports free Douyin (抖音) video download and text extraction.
- Allows users to input a Douyin video link to get a direct download URL.
- Provides an option to extract and return the video's text content.
- Step-by-step interactive process guides users through video link parsing, text extraction task submission, and status checking.
- Includes error checking for URL formats and user confirmations before actions.
Metadata
Frequently Asked Questions
What is 九马免费抖音视频下载和转文本?
九码AI免费抖音视频下载和文本提取技能。 It is an AI Agent Skill for Claude Code / OpenClaw, with 150 downloads so far.
How do I install 九马免费抖音视频下载和转文本?
Run "/install jiuma-free-video-to-text" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is 九马免费抖音视频下载和转文本 free?
Yes, 九马免费抖音视频下载和转文本 is completely free, licensed under MIT-0. You can download, install and use it at no cost.
Which platforms does 九马免费抖音视频下载和转文本 support?
九马免费抖音视频下载和转文本 is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created 九马免费抖音视频下载和转文本?
It is built and maintained by dddcn1 (@dddcn1); the current version is v1.0.4.
More Skills