see2023/Bert-VITS2-ext
基于Bert-VITS2做的表情、动画测试. Animation testing based on Bert-VITS2.
This project helps animators and content creators quickly generate natural facial expressions and body movements synchronized with spoken audio. You provide an audio file (like a voiceover or song), and it outputs animation data (e.g., Live Link Face values or skeletal rotations) that can drive virtual characters in animation software. This is for professionals creating virtual characters, animated content, or virtual assistants.
539 stars. No commits in the last 6 months.
Use this if you need to animate realistic facial expressions and body movements for digital characters directly from audio, without manual keyframing.
Not ideal if you primarily need high-fidelity, handcrafted animations or if your characters require highly complex, non-speech-driven movements.
Stars
539
Forks
58
Language
Python
License
AGPL-3.0
Category
Last pushed
Aug 06, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/voice-ai/see2023/Bert-VITS2-ext"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
RVC-Boss/GPT-SoVITS
1 min voice data can also be used to train a good TTS model! (few shot voice cloning)
High-Logic/Genie-TTS
GPT-SoVITS ONNX Inference Engine & Model Converter
chinokikiss/GSV-TTS-Lite
GSV-TTS-Lite A high-performance inference engine specifically designed for the GPT-SoVITS...
FENRlR/MB-iSTFT-VITS2
Application of MB-iSTFT-VITS components to vits2_pytorch
AlexandaJerry/vits-mandarin-biaobei
application of vits on mandarin tts