快速分享大模型生成的HTML、Markdown、SVG、Mermaid代码
Key Features
- 普通语音生成: Converts text to natural speech.
- 方言语音生成: Generates speech in various dialects (e.g., Sichuan dialect, Northeast dialect).
- 情感语音生成: Produces speech with different emotions (e.g., happy, excited, calm).
- 情感标记语音: Uses markers like [laughter] to control emotional changes in speech.
- 分段处理长文本: Supports processing long texts in segments, suitable for generating lengthy speech.
Benefits
- Easy to use with a simple command-line interface.
- Supports multiple languages and dialects, enhancing accessibility.
- Allows for emotional expression in generated speech, making it more engaging.
Highlights
- Requires Python 3.6+, PyTorch, and Torchaudio.
- Utilizes the CosyVoice2 model for high-quality voice generation.
- Provides a structured directory for easy management of models and assets.