# JiehangXie/PaddleBoBo

基于飞桨开发的虚拟主播

Repository: https://github.com/JiehangXie/PaddleBoBo
Canonical: https://ross.abutalabs.com/products/paddlebobo
Language: Python
License: GPL-3.0
License Family: copyleft
Last push: 2023-03-12T05:16:01+00:00

## Health v2 (maintenance only)
Score: 32/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 0, release rhythm 35, longevity 100
- inputs: {"age_days": 1715, "days_push": 1270, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1062, forks 298 (observed 2026-08-28T04:03:26.145102+00:00)

## What it is
PaddleBoBo is a Python project built on PaddlePaddle (with PaddleSpeech and PaddleGAN) that quickly generates a virtual streamer (VTuber) from a single portrait image and text input. It animates a static face via facial expression transfer, synthesizes speech with TTS, and supports both pre-rendered video generation and real-time live streaming.

## Use cases
- generate a virtual streamer video from a photo and text
- create an AI avatar that reads news scripts aloud
- run a real-time virtual host live stream on Bilibili
- animate a static face image with facial expressions
- customize TTS speech rate, pitch, and energy for an avatar voice

## When to choose
- you want a quick VTuber/avatar video generator using only one portrait photo
- you are already in the PaddlePaddle ecosystem (e.g., AIStudio with GPUs)
- you need both offline video generation and live streaming from the same pipeline

## When to avoid
- you lack an NVIDIA GPU with large VRAM or a cloud GPU environment
- you need a polished, actively maintained product rather than a demo-grade project
- you prefer PyTorch/TensorFlow-based animation toolkits like SadTalker or Wav2Lip

## Facets
- artifact type: application
- maturity: maintenance
- function: tts, video-processing, machine-learning, deep-learning, image-processing
- domain: artificial-intelligence, deep-learning, media
- platform: windows, python
- tags: virtual-youtuber, vtuber, face-animation, text-to-speech, paddlepaddle, live-streaming, avatar-generation, video, natural-language-processing, linux, macos, gpu

## Member repositories
- JiehangXie/PaddleBoBo (main) score 32

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:03:26.145102+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 2026-08-30T06:56:42.161740+00:00, confidence not recorded.
  - readme: https://github.com/JiehangXie/PaddleBoBo (fetched 2026-08-28T04:03:26.145102+00:00, sha d2c951841bed)
- Data as of 2026-08-30T08:39:29.467469+00:00.