# Jingyi-Wu-Richael/rachel-digital-human-production

Repository: https://github.com/Jingyi-Wu-Richael/rachel-digital-human-production
Canonical: https://ross.abutalabs.com/products/rachel-digital-human-production
Language: Python
License: MIT
License Family: permissive
Last push: 2026-07-16T11:03:38+00:00

## Health v2 (maintenance only)
Score: 54/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 92, release rhythm 35, longevity 3
- inputs: {"age_days": 48, "days_push": 48, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases, young
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1005, forks 156 (observed 2026-08-28T04:03:11.252617+00:00)

## What it is
A Codex skill (plugin) that packages a repeatable workflow for producing authorized digital-human talking-head videos using MiniMax voice cloning and HeyGen image-to-video APIs. It includes helper Python scripts for asset preflight checks, job state tracking, and a preview-first approval flow before paid 1080p generation.

## Use cases
- generate a talking-head video from a portrait photo and script
- clone a voice with minimax and narrate a digital human video
- create a 15-second ai avatar preview before committing to full 1080p render
- automate heygen image-to-video production with job state tracking
- validate script portrait and voice assets before paid api calls
- produce authorized digital human videos with a codex playbook

## When to choose
- you already have MiniMax and HeyGen API keys and want a structured, preview-first production workflow
- you use OpenAI Codex and want an explicitly invoked skill for digital-human video generation
- you need asset validation and job-state tracking around paid video generation APIs
- you want a repeatable playbook for authorized talking-head video production

## When to avoid
- you have no MiniMax or HeyGen accounts or API keys
- you want a standalone application with a GUI rather than a Codex-invoked skill
- you need free or local video generation without paid third-party APIs
- you intend to use it with unauthorized voice or portrait material

## Facets
- artifact type: plugin
- maturity: active
- function: video-processing, speech-recognition, tts, workflow-automation, sdk
- domain: artificial-intelligence, developer-tools
- platform: python, cli, cross-platform
- tags: digital-human, talking-head-video, voice-cloning, heygen, minimax, codex-skill, ai-avatar, video-generation, asset-preflight, job-state-tracking, video, audio, automation

## Member repositories
- Jingyi-Wu-Richael/rachel-digital-human-production (main) score 54

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:03:11.252617+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T07:13:05.475544+00:00, confidence not recorded.
  - readme: https://github.com/Jingyi-Wu-Richael/rachel-digital-human-production (fetched 2026-08-28T04:03:11.252617+00:00, sha e5bd9fe56408)
- Data as of 2026-08-30T08:39:29.467469+00:00.