We built NeuTTS-2E, an open-source on-device TTS model with 7 controllable emotions

We’re open sourcing an alpha release of NeuTTS-2E: an on-device TTS model with 125M active parameters and 7 controllable emotions. The goal was simple: when you select “angry,” “fearful,” or “happy,” the delivery should follow that instruction rather than whatever emotion the model infers from

中文全文翻译正在补齐，可先查看下方英文原文。

We’re open sourcing an alpha release of NeuTTS-2E: an on-device TTS model with 125M active parameters and 7 controllable emotions. The goal was simple: when you select “angry,” “fearful,” or “happy,” the delivery should follow that instruction rather than whatever emotion the model infers from