A demo of Sherpa-Onnx Models and in particular the MMS model
Generate audio from text in multiple languages
Generate multilingual speech using text input
Generate voice audio from text input
Generate speech from text in multiple languages
text-to-image-to-text
Generate audio from text in multiple languages
Generate audio from text with various languages and styles
Generate audio from text in multiple languages
Generate voice from text
Generate audio from text in selected language
Microsoft Edge's Text To Speech
Translate and generate speech from text
Sherpa Onnx Tts is a demo application that showcases the capabilities of Sherpa-Onnx models, specifically the MMS (Multi-Dataset Multi-Speaker) model. It is designed to generate high-quality speech from text in multiple languages, making it a versatile tool for text-to-speech tasks.
• Multi-Language Support: Generate speech in various languages with high-quality output. • ONNX Model Optimization: Leveraging ONNX format for improved performance and compatibility. • MMS Model Integration: Utilizes the MMS model for robust text-to-speech synthesis. • High-Quality Audio: Produces natural and clear speech outputs. • Cross-Platform Compatibility: Can be used on multiple platforms for flexibility.
torchaudio and onnxruntime.What languages are supported by Sherpa Onnx Tts?
Sherpa Onnx Tts supports a variety of languages, including English, Mandarin, Spanish, and more, depending on the model configuration.
How do I install Sherpa Onnx Tts?
To install, clone the repository and install the required packages using pip install -r requirements.txt.
Can I use Sherpa Onnx Tts on mobile devices?
Yes, Sherpa Onnx Tts is optimized for cross-platform use, including mobile devices, thanks to the ONNX format.