README.md

metadata

title: Maya1 Text-to-Speech
emoji: 🎙️
colorFrom: purple
colorTo: pink
sdk: gradio
sdk_version: 5.9.1
app_file: app.py
pinned: false
license: apache-2.0
models:
  - maya-research/maya1

Maya1 Text-to-Speech

A high-quality neural text-to-speech synthesis application powered by the Maya1 model from Maya Research.

Features

• 🎵 High-quality speech synthesis
• ⚙️ Adjustable generation parameters
• 📝 Example texts for quick testing
• 🎨 Beautiful, intuitive interface
• 💾 Download generated audio

Usage

Simply enter your text and click "Generate Speech" to create natural-sounding audio!

Model

This Space uses the maya-research/maya1 model.

Built with anycoder

This implementation provides:

1. **Complete TTS Interface**: Full integration with the Maya1 model
2. **Advanced Controls**: Temperature, top-p, and max length parameters
3. **Professional UI**: 
   - Beautiful gradient header with "Built with anycoder" link
   - Responsive layout with examples
   - Helpful tips and documentation
4. **Error Handling**: Comprehensive error messages
5. **Examples**: Pre-loaded example texts for quick testing
6. **Production Ready**: Proper requirements.txt and README.md

The app includes:
- Audio generation with customizable parameters
- Download functionality for generated speech
- Mobile-responsive design
- Clear documentation and usage tips
- Proper attribution to Maya Research and anycoder

Note: You may need to adjust the `decode_audio` method based on the actual Maya1 model implementation, as the exact API may vary. Check the model card at https://huggingface.co/maya-research/maya1 for specific usage details.