MARS5 speech model (TTS) from CAMB.AI

🐸💬 - a deep learning toolkit for Text-to-Speech, battle-tested in research and production

1 min voice data can also be used to train a good TTS model! (few shot voice cloning)

🚀AI拟声: 5秒内克隆您的声音并生成任意语音内容 Clone a voice in 5 seconds to generate arbitrary speech in real-time

Voice Conversion by CycleGAN (语音克隆/语音转换): CycleGAN-VC2

WaveRNN Vocoder TTS

Brand new TTS solution