# modstart-lib/aigcpanel

AIGCPanel 是一个简单易用的一站式AI数字人系统，支持视频合成、声音合成、声音克隆，简化本地模型管理、一键导入和使用AI模型。

Repository: https://github.com/modstart-lib/aigcpanel
Canonical: https://ross.abutalabs.com/products/aigcpanel
Homepage: https://aigcpanel.com
Language: TypeScript
License: Apache-2.0
License Family: permissive
Topics: cosyvoice, ai, musetalk, latentsync, wav2lip, aigc, sparktts, fishspeech
Last push: 2026-08-22T07:45:50+00:00

## Health v2 (maintenance only)
Score: 88/100 (v2, computed 2026-09-03T02:39:23.370411+00:00)
- activity 99, release rhythm 98, longevity 48
- inputs: {"age_days": 684, "days_push": 11, "days_rel": 13, "gap_med": 14.0, "n_releases_24m": 27}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 5482, forks 821 (observed 2026-08-28T04:09:19.717521+00:00)

## What it is
AIGCPanel is an open-source, all-in-one AI digital human desktop application built with TypeScript, Vue3, and Electron for Windows, macOS, and Linux. It lets non-technical users synthesize lip-synced avatar videos, run text-to-speech and voice cloning, manage local or remote AI models with one-click imports, and access 25+ audio/video tools plus optional visual workflow and livestream features.

## Use cases
- generate lip-synced digital human videos from text or audio
- clone a voice from a reference audio clip
- convert long text to speech with local TTS models
- transcribe audio to timestamped subtitles
- manage and run local AI models with one click
- replace a video's audio track with synthesized speech
- automate AI creation pipelines with a visual workflow
- run an AI avatar livestream with danmaku interaction

## When to choose
- you want a beginner-friendly GUI for digital human video and voice generation
- you need to run open-source TTS/ASR/lip-sync models locally without CLI setup
- you want bundled audio/video editing tools alongside AI generation
- you prefer offline, local processing of AI media tasks

## When to avoid
- you need programmatic APIs or headless server-side batch generation
- you require Linux support as a first-class stable platform
- you need the livestream or workflow features without paying for the Pro/VIP tier
- your GPU is below the recommended specs and you don't want cloud model services

## Facets
- artifact type: application
- maturity: active
- function: llm-inference, tts, speech-recognition, video-processing, audio-processing, image-processing, gui, workflow-automation, chatbot
- domain: artificial-intelligence, large-language-models, speech-processing, media, developer-tools, cross-platform
- platform: windows
- tags: digital-human, lip-sync, voice-cloning, tts, asr, model-management, livestream, aigc, musetalk, cosyvoice, wav2lip, latentsync, video, audio, macos, linux, desktop, electron, typescript

## Member repositories
- modstart-lib/aigcpanel (main) score 88

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:09:19.717521+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 2026-08-29T17:56:22.664699+00:00, confidence not recorded.
  - readme: https://github.com/modstart-lib/aigcpanel (fetched 2026-08-28T04:09:19.717521+00:00, sha a943b0bbbb40)
  - homepage: https://aigcpanel.com (fetched 2026-08-29T08:51:55.591122+00:00, sha b4173b81dcb1)
- Data as of 2026-08-30T08:39:29.467469+00:00.