开源的、模块化的GPT-4级语音对话系统

语音克隆

VoxCPM: Tokenizer-Free TTS for Context-Aware Speech Generation and True-to-Life Voice Cloning

文字转语音 https://chattts.com/ 方言: https://github.com/rany2/edge-tts https://mp.weixin.qq.com/s/HhIE3QUfr6kh6-6jA2Tk_g

OpenVoice https://mp.weixin.qq.com/s/QDPX7D1mnwwmmv1pb_TbOA

文字 转 语音

ElevenLabs

https://ttsmaker.com/

google bart open-source text-to-speech+ model. https://github.com/suno-ai/bark

https://www.notta.ai/en

说话者识别

A Repository for Single- and Multi-modal Speaker Verification, Speaker Recognition and Speaker Diarization

Silero VAD: pre-trained enterprise-grade Voice Activity Detector

实时语音

Multilingual Voice Understanding Model

VibeVoice

语音翻译

rask ai https://www.rask.ai/

电子书

Generate audiobooks from e-books, voice cloning & 1158+ languages!

播客

SoulX-Podcast