README.md

metadata

title: VoiceDemo
emoji: 🎤
colorFrom: blue
colorTo: purple
sdk: gradio
sdk_version: 6.4.0
app_file: app.py
pinned: false

Microsoft SpeechT5 Text-to-Speech Demo

A HuggingFace Space demo showcasing the Microsoft SpeechT5 text-to-speech model.

🎯 Features

• High-quality speech synthesis: Convert text to natural-sounding speech
• Multi-language support: Supports both English and Chinese text
• Real-time generation: Fast and efficient speech generation
• User-friendly interface: Simple Gradio-based web interface

🚀 Usage

1. Enter your text in the input box
2. Click "Generate Speech" or press Enter
3. Listen to the generated audio
4. Download the audio file if desired

💡 Examples

Try these example texts:

• "Hello, welcome to the Microsoft SpeechT5 text-to-speech demo!"
• "The quick brown fox jumps over the lazy dog."
• "今天天气真好，适合出去散步。"

🔧 Technical Details

• Model: Microsoft SpeechT5
• Framework: PyTorch + Transformers
• Interface: Gradio
• Sample Rate: 16kHz

📦 Dependencies

See requirements.txt for complete dependency list.

---

Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference