Transcribe video links
Turn supported public video links or share text into reusable transcript text.
Video subtitle extraction Skill
Let your AI agent extract video text and timestamped subtitles
Use the Videosays Skill when you need video transcription, subtitle extraction, or spoken text from a supported public video link. It returns clean text, timelines, SRT, or VTT for the agent to use next.
The Videosays skill tells the agent how to check authentication, submit transcription tasks, poll long-running jobs, and handle credit or media errors.
Prompt
Read https://videosays.com/SKILL.md, install the Videosays Skill if your environment supports skills, and help me transcribe this public video link.
1You ask your AI agent to transcribe or subtitle a video link.
2The agent reads the Videosays skill instructions.
3The skill uses the Videosays CLI under the hood.
Export usable formats
Return plain text, timestamped timelines, SRT subtitles, or VTT subtitles.
Handle long tasks
Use task status polling when transcription takes longer than the first command wait.
Explain next steps
Surface insufficient credits, unsupported media, or inaccessible links in plain language.
When an agent should use this Skill
- The user asks to extract subtitles or spoken text from a video.
- The user sends a short-video link and asks for a summary, script, or notes.
- The user needs timestamped text, SRT subtitles, or VTT subtitles.
- The user wants Douyin, TikTok, Instagram, X, YouTube, Bilibili, Xiaohongshu, Kuaishou, or WeChat Channels video content in text form.
Connect your agent
Use the option that matches your agent environment. The public SKILL.md is the universal fallback.
ClawHub
clawhub install @wegofuture/videosays
SkillUse
skilluse repo add xwchris/videosays-agent-tools --path skills --branch main --default skilluse install videosays --agent codex --global
npx skills
npx skills add xwchris/videosays-agent-tools npx skills use xwchris/videosays-agent-tools --skill videosays
Direct prompt
Read https://videosays.com/SKILL.md, install the Videosays Skill if your environment supports skills, and help me transcribe this public video link.
How it works
- 1
You ask your AI agent to transcribe or subtitle a video link.
- 2
The agent reads the Videosays skill instructions.
- 3
The skill uses the Videosays CLI under the hood.
- 4
Videosays returns transcript text or the requested subtitle format.
- 5
Your agent can then summarize, rewrite, archive, or continue the workflow.