1 min voice data can also be used to train a good TTS model! (few shot voice cloning)
Repository Index
47,133 repositories indexed
1–5 of 5 · Most stars
The open-source AI voice studio. Clone, dictate, create.
Instant voice cloning by MIT and MyShell. Audio foundation model.
An Industrial-Level Controllable and Efficient Zero-Shot Text-To-Speech System
语音 AI 女友（Voice AI girlfriend for DeepSeek Harness）：Whisper 语音输入 + Qwen3-TTS 声音克隆 + 句子级流式朗读 + 数字人动画窗。插话/排队双模式，说话即打断。