昨天玩了下站内佬的虚拟伴侣项目,成功跑起来了:
github.com
GitHub - Open-LLM-VTuber/Open-LLM-VTuber: Talk to any LLM with hands-free voice interaction,...
Talk to any LLM with hands-free voice interaction, voice interruption, and Live2D taking face running locally across platforms
现在想搞个声音克隆,让ai回答的时候文字转成克隆的tts;
在站内查了下,相关的帖子大多都是半年前一年前的了。。。
大概查到这些:
- GitHub - RVC-Boss/GPT-SoVITS: 1 min voice data can also be used to train a good TTS model! (few shot voice cloning) · GitHub
- GitHub - index-tts/index-tts: An Industrial-Level Controllable and Efficient Zero-Shot Text-To-Speech System · GitHub
- VoxCPM/README_zh.md at main · OpenBMB/VoxCPM · GitHub
- 声音复刻简介_声音复刻购买指南_声音复刻操作指南-腾讯云
- 音色快速复刻 - MiniMax 开放平台文档中心
我是更倾向于调api的方式(怕电脑跑不动),目前想着用minimax,但好像挺昂贵啊 ![]()
佬们有没有其他或者做成了的方案捏?
6 个帖子 - 6 位参与者