Lanshu AI Presenter Video skill
lanshu-create-ai-presenter-video
A skill for videos with a talking AI presenter from a script and one authorized portrait: narration, lip-sync, captions and verification of the result
- 2,646 ★ on the repository
- Last commit
- MIT
Broad access
Why this level
- An authorized portrait is needed: someone else's likeness cannot be used without consent
- The finished video must be marked as synthetic
- The skill calls paid services with your keys
Install
- Works in
Manual install
git clone https://github.com/cclank/lanshu-create-ai-presenter-video.gitClone it into the agent's skills folder. Python 3.9 or newer and FFmpeg are needed.
Access and checks
How we reviewBroad accessThe tool can change data, run commands or handle secrets.
- An authorized portrait is needed: someone else's likeness cannot be used without consent
- The finished video must be marked as synthetic
- The skill calls paid services with your keys
This is third-party code. Review the repository files before installing.
What it does
lanshu-create-ai-presenter-video leads an agent through the whole production of a presenter video: script, narration, presenter generation, lip-sync, captions and keywords. The skill is not tied to an agent or services: voice, presenter video and speech recognition are picked by capability, and the provider, model and parameters are saved in the job record. The approved narration sets one clock for presenter motion, captions and editing. It needs Python 3.9 or newer and FFmpeg. MIT license.
Who it is for. For authors of educational and promotional clips who make presenter videos from their own portrait.
Good fit when
- You need a clip with a presenter from your script and your portrait
- You need captions and lip-sync with the narration
- You need stage-by-stage checking of the result
Not a fit when
- You need someone else's likeness without consent: the skill requires an authorized portrait
- You need to pass a video off as a recording of a real person
Example request
Make a thirty-second clip with a presenter from my script and my portrait, with captions and stage checksLimitations
Use only your own portrait or the portrait of a person who gave written consent. The README requires an authorized portrait and a standard voice with no authorized sample. Mark the finished video as synthetic and do not pass it off as a recording of a real person. The skill uses paid voice and video generation services that you connect yourself. Access is extended.
How to disable. Delete the skill folder from the agent's folder and the generated videos. Revoke service keys where they were issued.
FAQ
Whose portrait can be used?
Only yours or that of a person who gave written consent: the README requires an authorized portrait.
What is needed to work?
Python 3.9 or newer, FFmpeg and voice and video generation services that you connect yourself.
Should the video be labeled?
Yes, mark the finished video as synthetic and do not pass it off as a recording of a real person.
Discussion
No questions or reviews yet.
Related
SkillsA skill that teaches the agent to build narrated videos through narrator-ai-cli: source, template, music, voice, script and composing
A skill that turns a topic into a narrated 4K video: research, script, local TTS, Remotion composition and an FFmpeg mix
Six skills that let the agent turn video into a short Chinese narration recap, locally via ffmpeg
A skill that turns a coding agent into a studio for voiceover explainer videos: word-level sync, a motion library and Remotion assembly
ChatGPT short-video editing skills
ChatGPT 剪短影音 Skills
Two agent skills: set up the editing environment and build a vertical short video in eight verified steps
A Claude Code and Codex skill that turns a topic into a narrated motion-graphics explainer video on Remotion with subtitles and chapters
Comparison with similar tools
Entries that share the main search query, and how they differ.
| Entry | Official | Repository stars | Main difference |
|---|---|---|---|
| Lanshu AI Presenter Video (this entry) | no | 2,646 | |
| Claude Code Video Toolkit | no | 2,206 | video production from script to MP4 render through Remotion |
| Claude Real Video | no | 2,216 | lets Claude watch other people's videos frame by frame |
| Motion Skills for AI agents | no | 789 | skills for animation and motion graphics in audience packs |
README in short
The README describes a skill for producing videos with a talking AI presenter from a script and an authorized portrait with narration, lip-sync and captions. MIT license.