# linyqh/NarratoAI

利用 AI 大模型，一键解说并剪辑视频

Repository: https://github.com/linyqh/NarratoAI
Canonical: https://ross.abutalabs.com/products/narratoai
Homepage: https://www.narratoai.cn
Language: Python
License: MIT
License Family: permissive
Topics: aiagent, aiops, llm, gemini-api, moviepy, python
Last push: 2026-08-26T02:49:46+00:00

## Health v2 (maintenance only)
Score: 88/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 99, release rhythm 93, longevity 53
- inputs: {"age_days": 751, "days_push": 7, "days_rel": 47, "gap_med": 14.0, "n_releases_24m": 31}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 10879, forks 1500 (observed 2026-08-28T04:10:44.578618+00:00)

## What it is
NarratoAI is an open-source, self-hosted AI-powered video commentary and automated editing tool. It uses large language models to generate narration scripts, then automates video editing, voiceover (TTS with voice cloning), subtitle generation, and AI-generated background music in a one-stop workflow.

## Use cases
- generate AI commentary narration for movies and TV shows
- automatically edit videos with voiceover and subtitles
- create short drama recap videos with LLMs
- clone voices for video narration
- transcribe subtitles from video automatically
- batch produce short-form video content for social media

## When to choose
- you want an end-to-end pipeline from LLM script writing to rendered video with narration and subtitles
- you need local deployment with multiple TTS engines including voice cloning on Apple Silicon
- you produce movie/drama commentary or recap content regularly

## When to avoid
- you need only simple trimming or manual video editing without AI narration
- you require a fully cloud-managed SaaS rather than a self-hosted Python app
- your workflow depends on non-OpenAI-compatible LLM APIs

## Facets
- artifact type: application
- maturity: active
- function: llm-inference, video-processing, tts, speech-recognition, agent-framework, workflow-automation
- domain: artificial-intelligence, large-language-models, media
- platform: python, cross-platform, windows, self-hosted
- tags: video-commentary, auto-editing, subtitles, voice-cloning, moviepy, gemini, content-creation, short-drama, video, automation, macos

## Member repositories
- linyqh/NarratoAI (main) score 88

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:10:44.578618+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 2026-08-29T17:17:27.011202+00:00, confidence not recorded.
  - readme: https://github.com/linyqh/NarratoAI (fetched 2026-08-28T04:10:44.578618+00:00, sha e2f2c754a92a)
  - homepage: https://www.narratoai.cn (fetched 2026-08-29T08:16:22.677291+00:00, sha 2d36b81e0bb4)
- Data as of 2026-08-30T08:39:29.467469+00:00.