语音技术学习笔记

几个关键概念

• TTS(Text-to-Speech): 根据输入文本生成音频
• SoVITS (Soft Voice Cloning): SoVITS(Soft Voice Imitation Transfer System), 克隆特定人的音色

语音服务商

• https://www.volcengine.com/docs/6561/192519

Real Time Agent

• https://livekit.io/

TTS(Text To Speech)开源项目:

ChatTTS:

• https://github.com/libukai/Awesome-ChatTTS/

• 基于ChatTTS，支持API Server和 Gradio WebUI: https://github.com/lenML/Speech-AI-Forge

  • https://huggingface.co/spaces/lenML/ChatTTS-Forge

• ChatTTS资源库： https://github.com/libukai/Awesome-ChatTTS/

GPT-SoVITS

• https://github.com/RVC-Boss/GPT-SoVITS

• https://github.com/babysor/MockingBird

  • 5s克隆声音

• https://github.com/myshell-ai/OpenVoice

  • myshell出品

https://github.com/openai/whisper