EmotiVoice
🔧 Toolnetease-youdao
Multi-voice, prompt-controlled TTS with emotional speech synthesis.
EmotiVoice is a PyTorch-based TTS engine that leverages a prompt-controlled mechanism to modulate speech emotion and style. It supports multiple speakers and a range of emotions such as happiness, sadness, anger, and surprise, controllable via textual prompts. The model architecture is designed for high-quality voice synthesis with fine-grained emotional expression. Key features include multi-voice support, emotion control through natural language prompts, and a flexible, open-source framework for customization. The project has gained significant attention (8.5k+ stars) and is actively maintained by NetEase Youdao, offering documentation and pre-trained models for quick deployment.
💡Highlights
- ├─8.5k GitHub stars
- ├─Prompt-controlled emotion
- └─Multi-speaker TTS
🎯For
- ├─TTS developers
- ├─AI researchers
- └─Voice app builders