kagari-bi / UmaChatLinks
Asset Viewer for Uma Musume
☆85Updated 2 years ago
Alternatives and similar repositories for UmaChat
Users that are interested in UmaChat are comparing it to the libraries listed below
Sorting:
- A webapi to help chatting with Umamusume☆38Updated 2 years ago
- ☆389Updated last year
- An Renpy enabled ver of ChatWaifu☆524Updated last year
- A convenient tool for generating audio files☆135Updated 2 years ago
- 利用Stable-Diffution API去除图片ai感☆77Updated last year
- ☆613Updated 2 years ago
- GUI for MoeGoe☆571Updated last year
- 桌面Live2D,提供自定义聊天接口,支持更换模型,自定义动作语音+文本☆195Updated 6 months ago
- VITS: Conditional Variational Autoencoder with Adversarial Learning for End-to-End Text-to-Speech☆166Updated last year
- Combined ChatGPT with Moegoe TTS to create a Chatting Waifu☆830Updated last year
- GPT + Tacotron2/VITS + Live2D = CyberWaifu☆87Updated 2 years ago
- 一个使用OpenAI接口链接VITS模型的语音对话系统GUI☆104Updated 2 years ago
- ☆82Updated last year
- 本地部署chatglm生成并以语音回复你的bilibili直播弹幕 Use chatglm to generate and reply your bilibili live danmu with voice☆251Updated 2 years ago
- Combining chatglm, vits, and pycqhttp for local deployment of qq chatbots.结合chatglm,vits,pycqhttp的本地部署qq聊天机器人。☆41Updated 2 years ago
- About Combined ChatGPT with Moegoe TTS to create a Chatting Waifu for Marai☆255Updated 2 years ago
- A naive webui for ChatGLM☆180Updated 2 years ago
- AI吟美零式☆71Updated last year
- An AI VTuber framework: ChatGPT + VITS + Live2D☆86Updated last year
- AI GAL是专门为Galgame场景设计的程序,旨在让得每一名用户都能享受到独一无二的剧情。程序基于renpy框架开发☆214Updated this week
- ☆31Updated 11 months ago
- ☆181Updated 3 months ago
- Fine-Tuning your VITS model using a pre-trained model☆551Updated 2 years ago
- An auxiliary tool for manual screening of audio dataset.☆127Updated 2 years ago
- vits2 backbone with bert☆341Updated last year
- VitsWebUi☆33Updated 2 years ago
- AI + Live2D + Real-Time-Voice实时语音识别和朗读,数字伙伴2D免费版,支持Live2D☆55Updated last year
- SoVits Gradio(Web UI)☆26Updated 2 years ago
- 语音合成项目☆163Updated 2 years ago
- 用于快速扬声器自适应TTS和任意语音转换 This repo is a pipeline of VITS finetuning for fast speaker adaptation TTS, and any-to-any voice conversion☆39Updated last year