talking-head-video — Claude Code skill: video, install
This skill creates talking-head videos from scripts, photos, or audio. Use it for AI presenters, lip-sync avatars, training clips, and multilingual content.
npx skills add eachlabs/skills --skill talking-head-video -a claude-codeWhat talking-head-video does
talking-head-video sends requests to each::sense AI to make presenter videos from a written script, a portrait, or an audio track. It can animate a still image, match mouth movement to existing speech, and shape the presenter’s delivery with different expressions.
You can describe a corporate spokesperson, training instructor, news anchor, or product explainer in the request. Supported outputs include portrait 1080x1920, landscape 1920x1080, and square 1080x1080 video up to 60s; headshot output is 720x720 for up to 30s.
The request uses the EACHLABS_API_KEY header with https://eachsense-agent.core.eachlabs.run/v1/chat/completions. The API key is required for the request to work.
What it helps with
- make a presenter video from a script
- animate a still portrait
- sync lip movement to an audio track
- produce a corporate spokesperson clip
- build a training video with an AI instructor
Example prompts for the agent
- Create a talking-head video with an AI presenter using this script: “Welcome to the course.”
- Animate
portrait.jpgwith natural speech and a 16:9 layout. - Sync the portrait to
voiceover.mp3and match the mouth movement to the audio.
How to install talking-head-video
1Skills CLI (Vercel)
npx skills add eachlabs/skills --skill talking-head-video -a claude-code2Manually: put the files in place
~/.claude/skills/talking-head-video/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/talking-head-video/
1Skills CLI (Vercel)
npx skills add eachlabs/skills --skill talking-head-video -a codex2Manually: put the files in place
.agents/skills/talking-head-video/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add eachlabs/skills --skill talking-head-video -a cursor2Manually: put the files in place
.cursor/skills/talking-head-video/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install eachlabs/skills talking-head-video2Manually: put the files in place
.github/skills/talking-head-video/SKILL.md1Skills CLI (Vercel)
npx skills add eachlabs/skills --skill talking-head-video -a gemini-cli2Platform CLI
gemini skills install https://github.com/eachlabs/skills --path skills/talking-head-videoManually: put the files in place
.devin/skills/talking-head-video/SKILL.mdThe legacy .windsurf/skills/ path still works
Skills CLI (Vercel)
npx skills add eachlabs/skills --skill talking-head-video -a opencodeClaude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
Step by step, with commands for each platform: How to install skills in Claude Code: five ways
Questions about talking-head-video
How do I install talking-head-video in Claude Code?
Run npx skills add eachlabs/skills --skill talking-head-video -a claude-code, then use ~/.claude/skills/talking-head-video/SKILL.md.
What does talking-head-video do?
It creates talking-head videos from scripts, photos, or audio. The skill covers AI presenters, lip-sync clips, corporate messages, and training content.
What video formats does talking-head-video support?
The listed outputs are portrait 1080x1920, landscape 1920x1080, and square 1080x1080 videos up to 60s. Headshot output uses 720x720 and runs up to 30s.
