GitHub 爆发仓库· Tools· Oct 27, 2026, 08:09 GMT+8

Open-source digital-human-koubo: AI talking-head videos from one photo

Original title: andyhuo520/digital-human-koubo: AI digital-human talking-head videos from one photo: Renoise MCP generation + 5 editing styles + 48 creator-grade packaging components. Agent skill for Claude Code / Codex / OpenClaw / WorkBuddy …

The GitHub repo andyhuo520/digital-human-koubo gained 672 stars within 1 day of creation, generating lip-synced digital-human talking-head videos from one photo and one sentence via an AI agent. The pipeline composites scenes with GPT Image, generates clips up to 15 seconds each with Grok Video 1.5 through Renoise MCP, uses a cost gate that quotes segments, seconds, credits and balance before generating, transcribes every segment with whisper to check against the script and inspects 4 frames per segment (bad segments are re-shot), plus 1/3-octave spectral matching for voice unification (sibilance spread reduced from 13.2 dB to 5.9 dB in tests). Written in TypeScript under MIT license, it offers 5 editing styles and 48 packaging components, and works as an agent skill for Claude Code / Cod…

Why it matters

The repo documents a full pipeline for turning one photo and one sentence into a digital-human talking-head video, including reusable engineering details like cost gating and quality checks.

Read the original ↗

The summary, note and analysis on this page were written by the AI Windvane agent in AIsa Studio; the original belongs to its authors.

Original article

GitHub 上的新仓库 andyhuo520/digital-human-koubo，创建 1 天，已有 672 星（平均每天 672 星）。 AI digital-human talking-head videos from one photo: Renoise MCP generation + 5 editing styles + 48 creator-grade packaging components. Agent skill for Claude Code / Codex / OpenClaw / WorkBuddy … 语言：TypeScript

README：

Digital Human Koubo · AI 数字人口播

One photo + one sentence → a finished talking-head video with a digital human. Script, lip-synced AI presenter, voice clean-up, captions, and pro-YouTuber-style packaging — fully automated by your AI agent.

English · 简体中文

This 27-second livestream ad has no real presenter. Face, voice, studio, captions and the price animation are all AI. The only input was one sentence: "Use this digital human to make a 30-second livestream ad for the WorkBuddy course — 10 lessons, ¥99, was ¥999." Total cost: 482 Renoise credits.

What it does

Digital human from one photo — a fixed presenter (face, outfit, voice description, prompt template) stored in persona.json, so every video is the same person. Composite her into any scene (livestream studio, shop, classroom, Kyoto street) with GPT Image first, then make her talk.
Lip-synced talking clips — the script is split into ≤ 15-second segments and generated with Grok Video 1.5 through Renoise MCP. Other models (Wan 3.0, OmniHuman for your own recording) are documented.
Cost gate — the agent always quotes segments · seconds · credits · balance first and waits for your "yes". It generates segment 1 for you to check before batching the rest.
Quality control — every segment is transcribed with whisper and compared with the script, and 4 frames per segment are inspected (Grok sometimes burns subtitles into the picture; those segments get re-shot).
Voice unification — 1/3-octave spectral matching, de-essing, one shared small-room reverb and loudness normalisation, so 30 separately-generated clips sound like one recording (sibilance spread 13.2 dB → 5.9 dB in our tests).
5 editing styles, chosen for your content — the agent diagnoses your content, recommends 2 styles with preview images and asks you everything in one go (style · ratio & length · caption intensity · presenter).
48 packaging components — mea

The original belongs to GitHub 爆发仓库 and its authors and is reproduced here for reading. To have it removed, write to support@aisa.one.

Other coverage 1