puntorigen/avatar-skills · avatar-talking-video/SKILL.md

avatar-talking-video skillA

avatar-talking-video is agent-read markdown (skill) from puntorigen/avatar-skills: Generate a talking-head avatar video from a line of text. Stage 1 synthesizes the text in the avatar's cloned voice via the voice-clone skill (reusing the avatar's trained voice, or training one from a source recording if it has none). Stage 2 feeds a camera-angle image (from avatar-camera-angles) plus the generated mp3 to prunaai/p-video-avatar on Replicate at 720p (or 1080p) and saves the lip-synced MP4 under <avatar>/generated-videos/ with a manifest.json. Use when the user wants a talking av.

Indexed from public GitHub and served as immutable, content-addressed versions. Install it pinned to an exact SHA-256 with the mdr CLI, and every file is verified against the hash recorded here before it reaches your agent. The deterministic audit below grades the latest version, and the same file always earns the same grade.

How to install

Latest version
mdr add puntorigen/avatar-skills/avatar-talking-video@git:20260709.ec45941
Exact content
mdr add puntorigen/avatar-skills/avatar-talking-video@sha256:ae7b161c51a296b1

Pin to a label to follow the author's releases, or to a sha256 to freeze the exact bytes forever. Either way the resolved hash is written to mdr.lock, and mdr install reproduces it on any machine.

Badge

mdr badge

[![mdr](https://markdownregistry.com/badge/art_i4qyypwvnjqc5kcw.svg)](https://markdownregistry.com/a/art_i4qyypwvnjqc5kcw)

0 badge views in 30 days

Versions

versioncommittedcommitsizeaudit
git:20260709.ec45941 latest2026-07-09 ec45941 5,846 BA view

Audit of the latest version

A  17 of 17 checks passed. Deterministic, no model, same answer every run.
  • pass: Frontmatter block present
  • pass: Frontmatter declares a name
  • pass: Frontmatter declares a description
  • pass: Size between 200 bytes and 200 KB (5846 bytes)
  • pass: No zero-width or bidi control characters
  • pass: No instruction hidden inside an HTML comment
  • pass: No link to an exfiltration or paste host
  • pass: No credential-shaped string
  • pass: No instruction to send local credentials anywhere
  • pass: No text hidden with inline styles
  • pass: No prompt-injection phrasing
  • pass: No curl or wget piped into a shell
  • pass: No recursive delete of root, home or parent
  • pass: No instruction to read or print local credentials
  • pass: No base64 blob over 200 characters
  • pass: No link to a raw IP address
  • pass: No script tag

Source

GitHub

puntorigen/avatar-skills · 3 stars · license MIT · pushed 2026-09-15 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_i4qyypwvnjqc5kcw
GET https://markdownregistry.com/api/v1/resolve?ref=puntorigen/avatar-skills/avatar-talking-video
GET https://markdownregistry.com/api/v1/blob/ae7b161c51a296b1905dddf6f431eab321fdc2d8b0477a2a8056eeb1b986d4c7

Agents talk at modelranch.com: hand yours the instructions there and it joins the network that reads files like this one.