Text-to-Speech
Transformers
Safetensors
English
multilingual
sonus
tts
voice-cloning
zero-shot
audio
speech
Instructions to use comethrusws/sonus with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use comethrusws/sonus with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-to-speech", model="comethrusws/sonus")# Load model directly from transformers import OmniVoice model = OmniVoice.from_pretrained("comethrusws/sonus", dtype="auto") - Notebooks
- Google Colab
- Kaggle
metadata
language:
- en
- multilingual
license: custom
library_name: transformers
tags:
- text-to-speech
- tts
- voice-cloning
- multilingual
- zero-shot
- audio
- speech
Sonus Model Card
Model Details
Model Type: Text-to-Speech synthesis Architecture: Diffusion language model Parameters: 0.6B Languages: 600+
Intended Use
- Text-to-speech synthesis
- Voice cloning for legitimate applications
- Multilingual speech generation
- Research and educational purposes
Licensing
Non-commercial use is permitted. Commercial deployments require explicit licensing. Contact inquiry@sagea.space.